Hotfix release (#907)

* Revert to old-fashion face store

* Bump release

* Don't be evil

* Don't be evil

.flake8

@@ -1,5 +1,5 @@
 [flake8]
-select = E3, E4, F, I1, I2
+select = E22, E23, E24, E27, E3, E4, E7, F, I1, I2
 per-file-ignores = facefusion.py:E402, install.py:E402
 plugins = flake8-import-order
 application_import_names = facefusion

.github/FUNDING.yml

@@ -1,2 +1 @@
-github: henryruhs
-custom: [ buymeacoffee.com/henryruhs, paypal.me/henryruhs ]
+custom: [ buymeacoffee.com/facefusion, ko-fi.com/facefusion ]

.github/workflows/ci.yml

@@ -8,10 +8,10 @@ jobs:
   steps:
   - name: Checkout
     uses: actions/checkout@v4
-  - name: Set up Python 3.10
+  - name: Set up Python 3.12
     uses: actions/setup-python@v5
     with:
-     python-version: '3.10'
+     python-version: '3.12'
   - run: pip install flake8
   - run: pip install flake8-import-order
   - run: pip install mypy
@@ -22,17 +22,17 @@ jobs:
  test:
   strategy:
    matrix:
-    os: [ macos-13, ubuntu-latest, windows-latest ]
+    os: [ macos-latest, ubuntu-latest, windows-latest ]
   runs-on: ${{ matrix.os }}
   steps:
   - name: Checkout
     uses: actions/checkout@v4
   - name: Set up FFmpeg
-    uses: FedericoCarboni/setup-ffmpeg@v3
-  - name: Set up Python 3.10
+    uses: AnimMouse/setup-ffmpeg@v1
+  - name: Set up Python 3.12
     uses: actions/setup-python@v5
     with:
-     python-version: '3.10'
+     python-version: '3.12'
   - run: python install.py --onnxruntime default --skip-conda
   - run: pip install pytest
   - run: pytest
@@ -44,10 +44,10 @@ jobs:
     uses: actions/checkout@v4
   - name: Set up FFmpeg
     uses: FedericoCarboni/setup-ffmpeg@v3
-  - name: Set up Python 3.10
+  - name: Set up Python 3.12
     uses: actions/setup-python@v5
     with:
-     python-version: '3.10'
+     python-version: '3.12'
   - run: python install.py --onnxruntime default --skip-conda
   - run: pip install coveralls
   - run: pip install pytest

.gitignore

@@ -1,3 +1,4 @@
+__pycache__
 .assets
 .caches
 .jobs

LICENSE.md

@@ -1,3 +1,3 @@
-MIT license
+OpenRAIL-AS license
 
-Copyright (c) 2024 Henry Ruhs
+Copyright (c) 2025 Henry Ruhs

README.md

@@ -5,7 +5,7 @@ FaceFusion
 
 [![Build Status](https://img.shields.io/github/actions/workflow/status/facefusion/facefusion/ci.yml.svg?branch=master)](https://github.com/facefusion/facefusion/actions?query=workflow:ci)
 [![Coverage Status](https://img.shields.io/coveralls/facefusion/facefusion.svg)](https://coveralls.io/r/facefusion/facefusion)
-![License](https://img.shields.io/badge/license-MIT-green)
+![License](https://img.shields.io/badge/license-OpenRAIL--AS-green)
 
 
 Preview
@@ -17,7 +17,7 @@ Preview
 Installation
 ------------
 
-Be aware, the [installation](https://docs.facefusion.io/installation) needs technical skills and is not recommended for beginners. In case you are not comfortable using a terminal, our [Windows Installer](https://windows-installer.facefusion.io) and [macOS Installer](https://macos-installer.facefusion.io) get you started.
+Be aware, the [installation](https://docs.facefusion.io/installation) needs technical skills and is not recommended for beginners. In case you are not comfortable using a terminal, our [Windows Installer](http://windows-installer.facefusion.io) and [macOS Installer](http://macos-installer.facefusion.io) get you started.
 
 
 Usage
@@ -35,7 +35,9 @@ options:
 commands:
     run                                           run the program
     headless-run                                  run the program in headless mode
+    batch-run                                     run the program in batch mode
     force-download                                force automate downloads and exit
+    benchmark                                     benchmark the program
     job-list                                      list jobs by status
     job-create                                    create a drafted job
     job-submit                                    submit a drafted job to become a queued job

facefusion.ini

@@ -1,9 +1,15 @@
 [paths]
+temp_path =
 jobs_path =
 source_paths =
 target_path =
 output_path =
 
+[patterns]
+source_pattern =
+target_pattern =
+output_pattern =
+
 [face_detector]
 face_detector_model =
 face_detector_size =
@@ -26,10 +32,13 @@ reference_face_distance =
 reference_frame_number =
 
 [face_masker]
+face_occluder_model =
+face_parser_model =
 face_mask_types =
+face_mask_areas =
+face_mask_regions =
 face_mask_blur =
 face_mask_padding =
-face_mask_regions =
 
 [frame_extraction]
 trim_frame_start =
@@ -41,17 +50,20 @@ keep_temp =
 output_image_quality =
 output_image_resolution =
 output_audio_encoder =
+output_audio_quality =
+output_audio_volume =
 output_video_encoder =
 output_video_preset =
 output_video_quality =
 output_video_resolution =
 output_video_fps =
-skip_audio =
 
 [processors]
 processors =
 age_modifier_model =
 age_modifier_direction =
+deep_swapper_model =
+deep_swapper_morph =
 expression_restorer_model =
 expression_restorer_factor =
 face_debugger_items =
@@ -72,6 +84,7 @@ face_editor_head_yaw =
 face_editor_head_roll =
 face_enhancer_model =
 face_enhancer_blend =
+face_enhancer_weight =
 face_swapper_model =
 face_swapper_pixel_boost =
 frame_colorizer_model =
@@ -80,12 +93,21 @@ frame_colorizer_blend =
 frame_enhancer_model =
 frame_enhancer_blend =
 lip_syncer_model =
+lip_syncer_weight =
 
 [uis]
 open_browser =
 ui_layouts =
 ui_workflow =
 
+[download]
+download_providers =
+download_scope =
+
+[benchmark]
+benchmark_resolutions =
+benchmark_cycle_count =
+
 [execution]
 execution_device_id =
 execution_providers =
@@ -97,5 +119,5 @@ video_memory_strategy =
 system_memory_limit =
 
 [misc]
-skip_download =
 log_level =
+halt_on_error =

facefusion/app_context.py

@@ -1,7 +1,7 @@
 import os
 import sys
 
-from facefusion.typing import AppContext
+from facefusion.types import AppContext
 
 
 def detect_app_context() -> AppContext:

facefusion/args.py

@@ -1,9 +1,9 @@
 from facefusion import state_manager
-from facefusion.filesystem import is_image, is_video, list_directory
+from facefusion.filesystem import get_file_name, is_image, is_video, resolve_file_paths
 from facefusion.jobs import job_store
 from facefusion.normalizer import normalize_fps, normalize_padding
 from facefusion.processors.core import get_processors_modules
-from facefusion.typing import ApplyStateItem, Args
+from facefusion.types import ApplyStateItem, Args
 from facefusion.vision import create_image_resolutions, create_video_resolutions, detect_image_resolution, detect_video_fps, detect_video_resolution, pack_resolution
 
 
@@ -15,6 +15,14 @@ def reduce_step_args(args : Args) -> Args:
 	return step_args
 
 
+def reduce_job_args(args : Args) -> Args:
+	job_args =\
+	{
+		key: args[key] for key in args if key in job_store.get_job_keys()
+	}
+	return job_args
+
+
 def collect_step_args() -> Args:
 	step_args =\
 	{
@@ -35,10 +43,15 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	# general
 	apply_state_item('command', args.get('command'))
 	# paths
+	apply_state_item('temp_path', args.get('temp_path'))
 	apply_state_item('jobs_path', args.get('jobs_path'))
 	apply_state_item('source_paths', args.get('source_paths'))
 	apply_state_item('target_path', args.get('target_path'))
 	apply_state_item('output_path', args.get('output_path'))
+	# patterns
+	apply_state_item('source_pattern', args.get('source_pattern'))
+	apply_state_item('target_pattern', args.get('target_pattern'))
+	apply_state_item('output_pattern', args.get('output_pattern'))
 	# face detector
 	apply_state_item('face_detector_model', args.get('face_detector_model'))
 	apply_state_item('face_detector_size', args.get('face_detector_size'))
@@ -48,20 +61,23 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_landmarker_model', args.get('face_landmarker_model'))
 	apply_state_item('face_landmarker_score', args.get('face_landmarker_score'))
 	# face selector
-	state_manager.init_item('face_selector_mode', args.get('face_selector_mode'))
-	state_manager.init_item('face_selector_order', args.get('face_selector_order'))
-	state_manager.init_item('face_selector_age_start', args.get('face_selector_age_start'))
-	state_manager.init_item('face_selector_age_end', args.get('face_selector_age_end'))
-	state_manager.init_item('face_selector_gender', args.get('face_selector_gender'))
-	state_manager.init_item('face_selector_race', args.get('face_selector_race'))
-	state_manager.init_item('reference_face_position', args.get('reference_face_position'))
-	state_manager.init_item('reference_face_distance', args.get('reference_face_distance'))
-	state_manager.init_item('reference_frame_number', args.get('reference_frame_number'))
+	apply_state_item('face_selector_mode', args.get('face_selector_mode'))
+	apply_state_item('face_selector_order', args.get('face_selector_order'))
+	apply_state_item('face_selector_age_start', args.get('face_selector_age_start'))
+	apply_state_item('face_selector_age_end', args.get('face_selector_age_end'))
+	apply_state_item('face_selector_gender', args.get('face_selector_gender'))
+	apply_state_item('face_selector_race', args.get('face_selector_race'))
+	apply_state_item('reference_face_position', args.get('reference_face_position'))
+	apply_state_item('reference_face_distance', args.get('reference_face_distance'))
+	apply_state_item('reference_frame_number', args.get('reference_frame_number'))
 	# face masker
+	apply_state_item('face_occluder_model', args.get('face_occluder_model'))
+	apply_state_item('face_parser_model', args.get('face_parser_model'))
 	apply_state_item('face_mask_types', args.get('face_mask_types'))
+	apply_state_item('face_mask_areas', args.get('face_mask_areas'))
+	apply_state_item('face_mask_regions', args.get('face_mask_regions'))
 	apply_state_item('face_mask_blur', args.get('face_mask_blur'))
 	apply_state_item('face_mask_padding', normalize_padding(args.get('face_mask_padding')))
-	apply_state_item('face_mask_regions', args.get('face_mask_regions'))
 	# frame extraction
 	apply_state_item('trim_frame_start', args.get('trim_frame_start'))
 	apply_state_item('trim_frame_end', args.get('trim_frame_end'))
@@ -77,6 +93,8 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 		else:
 			apply_state_item('output_image_resolution', pack_resolution(output_image_resolution))
 	apply_state_item('output_audio_encoder', args.get('output_audio_encoder'))
+	apply_state_item('output_audio_quality', args.get('output_audio_quality'))
+	apply_state_item('output_audio_volume', args.get('output_audio_volume'))
 	apply_state_item('output_video_encoder', args.get('output_video_encoder'))
 	apply_state_item('output_video_preset', args.get('output_video_preset'))
 	apply_state_item('output_video_quality', args.get('output_video_quality'))
@@ -90,9 +108,8 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	if args.get('output_video_fps') or is_video(args.get('target_path')):
 		output_video_fps = normalize_fps(args.get('output_video_fps')) or detect_video_fps(args.get('target_path'))
 		apply_state_item('output_video_fps', output_video_fps)
-	apply_state_item('skip_audio', args.get('skip_audio'))
 	# processors
-	available_processors = list_directory('facefusion/processors/modules')
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	apply_state_item('processors', args.get('processors'))
 	for processor_module in get_processors_modules(available_processors):
 		processor_module.apply_args(args, apply_state_item)
@@ -105,12 +122,18 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('execution_providers', args.get('execution_providers'))
 	apply_state_item('execution_thread_count', args.get('execution_thread_count'))
 	apply_state_item('execution_queue_count', args.get('execution_queue_count'))
+	# download
+	apply_state_item('download_providers', args.get('download_providers'))
+	apply_state_item('download_scope', args.get('download_scope'))
+	# benchmark
+	apply_state_item('benchmark_resolutions', args.get('benchmark_resolutions'))
+	apply_state_item('benchmark_cycle_count', args.get('benchmark_cycle_count'))
 	# memory
 	apply_state_item('video_memory_strategy', args.get('video_memory_strategy'))
 	apply_state_item('system_memory_limit', args.get('system_memory_limit'))
 	# misc
-	apply_state_item('skip_download', args.get('skip_download'))
 	apply_state_item('log_level', args.get('log_level'))
+	apply_state_item('halt_on_error', args.get('halt_on_error'))
 	# jobs
 	apply_state_item('job_id', args.get('job_id'))
 	apply_state_item('job_status', args.get('job_status'))

facefusion/audio.py

@@ -3,25 +3,26 @@ from typing import Any, List, Optional
 
 import numpy
 import scipy
-from numpy._typing import NDArray
+from numpy.typing import NDArray
 
 from facefusion.ffmpeg import read_audio_buffer
 from facefusion.filesystem import is_audio
-from facefusion.typing import Audio, AudioFrame, Fps, Mel, MelFilterBank, Spectrogram
+from facefusion.types import Audio, AudioFrame, Fps, Mel, MelFilterBank, Spectrogram
 from facefusion.voice_extractor import batch_extract_voice
 
 
-@lru_cache(maxsize = 128)
+@lru_cache()
 def read_static_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
 	return read_audio(audio_path, fps)
 
 
 def read_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
-	sample_rate = 48000
-	channel_total = 2
+	audio_sample_rate = 48000
+	audio_sample_size = 16
+	audio_channel_total = 2
 
 	if is_audio(audio_path):
-		audio_buffer = read_audio_buffer(audio_path, sample_rate, channel_total)
+		audio_buffer = read_audio_buffer(audio_path, audio_sample_rate, audio_sample_size, audio_channel_total)
 		audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, 2)
 		audio = prepare_audio(audio)
 		spectrogram = create_spectrogram(audio)
@@ -30,21 +31,22 @@ def read_audio(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
 	return None
 
 
-@lru_cache(maxsize = 128)
+@lru_cache()
 def read_static_voice(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
 	return read_voice(audio_path, fps)
 
 
 def read_voice(audio_path : str, fps : Fps) -> Optional[List[AudioFrame]]:
-	sample_rate = 48000
-	channel_total = 2
-	chunk_size = 240 * 1024
-	step_size = 180 * 1024
+	voice_sample_rate = 48000
+	voice_sample_size = 16
+	voice_channel_total = 2
+	voice_chunk_size = 240 * 1024
+	voice_step_size = 180 * 1024
 
 	if is_audio(audio_path):
-		audio_buffer = read_audio_buffer(audio_path, sample_rate, channel_total)
+		audio_buffer = read_audio_buffer(audio_path, voice_sample_rate, voice_sample_size, voice_channel_total)
 		audio = numpy.frombuffer(audio_buffer, dtype = numpy.int16).reshape(-1, 2)
-		audio = batch_extract_voice(audio, chunk_size, step_size)
+		audio = batch_extract_voice(audio, voice_chunk_size, voice_step_size)
 		audio = prepare_voice(audio)
 		spectrogram = create_spectrogram(audio)
 		audio_frames = extract_audio_frames(spectrogram, fps)
@@ -60,6 +62,20 @@ def get_audio_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Opti
 	return None
 
 
+def extract_audio_frames(spectrogram : Spectrogram, fps : Fps) -> List[AudioFrame]:
+	audio_frames = []
+	mel_filter_total = 80
+	audio_step_size = 16
+	indices = numpy.arange(0, spectrogram.shape[1], mel_filter_total / fps).astype(numpy.int16)
+	indices = indices[indices >= audio_step_size]
+
+	for index in indices:
+		start = max(0, index - audio_step_size)
+		audio_frames.append(spectrogram[:, start:index])
+
+	return audio_frames
+
+
 def get_voice_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Optional[AudioFrame]:
 	if is_audio(audio_path):
 		voice_frames = read_static_voice(audio_path, fps)
@@ -70,8 +86,8 @@ def get_voice_frame(audio_path : str, fps : Fps, frame_number : int = 0) -> Opti
 
 def create_empty_audio_frame() -> AudioFrame:
 	mel_filter_total = 80
-	step_size = 16
-	audio_frame = numpy.zeros((mel_filter_total, step_size)).astype(numpy.int16)
+	audio_step_size = 16
+	audio_frame = numpy.zeros((mel_filter_total, audio_step_size)).astype(numpy.int16)
 	return audio_frame
 
 
@@ -84,10 +100,10 @@ def prepare_audio(audio : Audio) -> Audio:
 
 
 def prepare_voice(audio : Audio) -> Audio:
-	sample_rate = 48000
-	resample_rate = 16000
-
-	audio = scipy.signal.resample(audio, int(len(audio) * resample_rate / sample_rate))
+	audio_sample_rate = 48000
+	audio_resample_rate = 16000
+	audio_resample_factor = round(len(audio) * audio_resample_rate / audio_sample_rate)
+	audio = scipy.signal.resample(audio, audio_resample_factor)
 	audio = prepare_audio(audio)
 	return audio
 
@@ -101,19 +117,20 @@ def convert_mel_to_hertz(mel : Mel) -> NDArray[Any]:
 
 
 def create_mel_filter_bank() -> MelFilterBank:
+	audio_sample_rate = 16000
+	audio_min_frequency = 55.0
+	audio_max_frequency = 7600.0
 	mel_filter_total = 80
 	mel_bin_total = 800
-	sample_rate = 16000
-	min_frequency = 55.0
-	max_frequency = 7600.0
 	mel_filter_bank = numpy.zeros((mel_filter_total, mel_bin_total // 2 + 1))
-	mel_frequency_range = numpy.linspace(convert_hertz_to_mel(min_frequency), convert_hertz_to_mel(max_frequency), mel_filter_total + 2)
-	indices = numpy.floor((mel_bin_total + 1) * convert_mel_to_hertz(mel_frequency_range) / sample_rate).astype(numpy.int16)
+	mel_frequency_range = numpy.linspace(convert_hertz_to_mel(audio_min_frequency), convert_hertz_to_mel(audio_max_frequency), mel_filter_total + 2)
+	indices = numpy.floor((mel_bin_total + 1) * convert_mel_to_hertz(mel_frequency_range) / audio_sample_rate).astype(numpy.int16)
 
 	for index in range(mel_filter_total):
 		start = indices[index]
 		end = indices[index + 1]
 		mel_filter_bank[index, start:end] = scipy.signal.windows.triang(end - start)
+
 	return mel_filter_bank
 
 
@@ -124,16 +141,3 @@ def create_spectrogram(audio : Audio) -> Spectrogram:
 	spectrogram = scipy.signal.stft(audio, nperseg = mel_bin_total, nfft = mel_bin_total, noverlap = mel_bin_overlap)[2]
 	spectrogram = numpy.dot(mel_filter_bank, numpy.abs(spectrogram))
 	return spectrogram
-
-
-def extract_audio_frames(spectrogram : Spectrogram, fps : Fps) -> List[AudioFrame]:
-	mel_filter_total = 80
-	step_size = 16
-	audio_frames = []
-	indices = numpy.arange(0, spectrogram.shape[1], mel_filter_total / fps).astype(numpy.int16)
-	indices = indices[indices >= step_size]
-
-	for index in indices:
-		start = max(0, index - step_size)
-		audio_frames.append(spectrogram[:, start:index])
-	return audio_frames

facefusion/benchmarker.py

@@ -0,0 +1,106 @@
+import hashlib
+import os
+import statistics
+import tempfile
+from time import perf_counter
+from typing import Generator, List
+
+import facefusion.choices
+from facefusion import core, state_manager
+from facefusion.cli_helper import render_table
+from facefusion.download import conditional_download, resolve_download_url
+from facefusion.filesystem import get_file_extension
+from facefusion.types import BenchmarkCycleSet
+from facefusion.vision import count_video_frame_total, detect_video_fps, detect_video_resolution, pack_resolution
+
+
+def pre_check() -> bool:
+	conditional_download('.assets/examples',
+	[
+		resolve_download_url('examples-3.0.0', 'source.jpg'),
+		resolve_download_url('examples-3.0.0', 'source.mp3'),
+		resolve_download_url('examples-3.0.0', 'target-240p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-360p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-540p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-720p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-1080p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-1440p.mp4'),
+		resolve_download_url('examples-3.0.0', 'target-2160p.mp4')
+	])
+	return True
+
+
+def run() -> Generator[List[BenchmarkCycleSet], None, None]:
+	benchmark_resolutions = state_manager.get_item('benchmark_resolutions')
+	benchmark_cycle_count = state_manager.get_item('benchmark_cycle_count')
+
+	state_manager.init_item('source_paths', [ '.assets/examples/source.jpg', '.assets/examples/source.mp3' ])
+	state_manager.init_item('face_landmarker_score', 0)
+	state_manager.init_item('temp_frame_format', 'bmp')
+	state_manager.init_item('output_audio_volume', 0)
+	state_manager.init_item('output_video_preset', 'ultrafast')
+	state_manager.init_item('video_memory_strategy', 'tolerant')
+
+	benchmarks = []
+	target_paths = [facefusion.choices.benchmark_set.get(benchmark_resolution) for benchmark_resolution in benchmark_resolutions if benchmark_resolution in facefusion.choices.benchmark_set]
+
+	for target_path in target_paths:
+		state_manager.set_item('target_path', target_path)
+		state_manager.set_item('output_path', suggest_output_path(state_manager.get_item('target_path')))
+		benchmarks.append(cycle(benchmark_cycle_count))
+		yield benchmarks
+
+
+def cycle(cycle_count : int) -> BenchmarkCycleSet:
+	process_times = []
+	video_frame_total = count_video_frame_total(state_manager.get_item('target_path'))
+	output_video_resolution = detect_video_resolution(state_manager.get_item('target_path'))
+	state_manager.set_item('output_video_resolution', pack_resolution(output_video_resolution))
+	state_manager.set_item('output_video_fps', detect_video_fps(state_manager.get_item('target_path')))
+
+	core.conditional_process()
+
+	for index in range(cycle_count):
+		start_time = perf_counter()
+		core.conditional_process()
+		end_time = perf_counter()
+		process_times.append(end_time - start_time)
+
+	average_run = round(statistics.mean(process_times), 2)
+	fastest_run = round(min(process_times), 2)
+	slowest_run = round(max(process_times), 2)
+	relative_fps = round(video_frame_total * cycle_count / sum(process_times), 2)
+
+	return\
+	{
+		'target_path': state_manager.get_item('target_path'),
+		'cycle_count': cycle_count,
+		'average_run': average_run,
+		'fastest_run': fastest_run,
+		'slowest_run': slowest_run,
+		'relative_fps': relative_fps
+	}
+
+
+def suggest_output_path(target_path : str) -> str:
+	target_file_extension = get_file_extension(target_path)
+	return os.path.join(tempfile.gettempdir(), hashlib.sha1().hexdigest()[:8] + target_file_extension)
+
+
+def render() -> None:
+	benchmarks = []
+	headers =\
+	[
+		'target_path',
+		'cycle_count',
+		'average_run',
+		'fastest_run',
+		'slowest_run',
+		'relative_fps'
+	]
+
+	for benchmark in run():
+		benchmarks = benchmark
+
+	contents = [ list(benchmark_set.values()) for benchmark_set in benchmarks ]
+	render_table(headers, contents)

facefusion/choices.py

@@ -2,32 +2,140 @@ import logging
 from typing import List, Sequence
 
 from facefusion.common_helper import create_float_range, create_int_range
-from facefusion.typing import Angle, ExecutionProviderSet, FaceDetectorSet, FaceLandmarkerModel, FaceMaskRegion, FaceMaskType, FaceSelectorMode, FaceSelectorOrder, Gender, JobStatus, LogLevelSet, OutputAudioEncoder, OutputVideoEncoder, OutputVideoPreset, Race, Score, TempFrameFormat, UiWorkflow, VideoMemoryStrategy
-
-video_memory_strategies : List[VideoMemoryStrategy] = [ 'strict', 'moderate', 'tolerant' ]
+from facefusion.types import Angle, AudioEncoder, AudioFormat, AudioTypeSet, BenchmarkResolution, BenchmarkSet, DownloadProvider, DownloadProviderSet, DownloadScope, EncoderSet, ExecutionProvider, ExecutionProviderSet, FaceDetectorModel, FaceDetectorSet, FaceLandmarkerModel, FaceMaskArea, FaceMaskAreaSet, FaceMaskRegion, FaceMaskRegionSet, FaceMaskType, FaceOccluderModel, FaceParserModel, FaceSelectorMode, FaceSelectorOrder, Gender, ImageFormat, ImageTypeSet, JobStatus, LogLevel, LogLevelSet, Race, Score, TempFrameFormat, UiWorkflow, VideoEncoder, VideoFormat, VideoMemoryStrategy, VideoPreset, VideoTypeSet, WebcamMode
 
 face_detector_set : FaceDetectorSet =\
 {
 	'many': [ '640x640' ],
 	'retinaface': [ '160x160', '320x320', '480x480', '512x512', '640x640' ],
 	'scrfd': [ '160x160', '320x320', '480x480', '512x512', '640x640' ],
-	'yoloface': [ '640x640' ]
+	'yolo_face': [ '640x640' ]
 }
+face_detector_models : List[FaceDetectorModel] = list(face_detector_set.keys())
 face_landmarker_models : List[FaceLandmarkerModel] = [ 'many', '2dfan4', 'peppa_wutz' ]
 face_selector_modes : List[FaceSelectorMode] = [ 'many', 'one', 'reference' ]
 face_selector_orders : List[FaceSelectorOrder] = [ 'left-right', 'right-left', 'top-bottom', 'bottom-top', 'small-large', 'large-small', 'best-worst', 'worst-best' ]
-face_selector_genders : List[Gender] = ['female', 'male']
-face_selector_races : List[Race] = ['white', 'black', 'latino', 'asian', 'indian', 'arabic']
-face_mask_types : List[FaceMaskType] = [ 'box', 'occlusion', 'region' ]
-face_mask_regions : List[FaceMaskRegion] = [ 'skin', 'left-eyebrow', 'right-eyebrow', 'left-eye', 'right-eye', 'glasses', 'nose', 'mouth', 'upper-lip', 'lower-lip' ]
-temp_frame_formats : List[TempFrameFormat] = [ 'bmp', 'jpg', 'png' ]
-output_audio_encoders : List[OutputAudioEncoder] = [ 'aac', 'libmp3lame', 'libopus', 'libvorbis' ]
-output_video_encoders : List[OutputVideoEncoder] = [ 'libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf', 'h264_videotoolbox', 'hevc_videotoolbox' ]
-output_video_presets : List[OutputVideoPreset] = [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]
+face_selector_genders : List[Gender] = [ 'female', 'male' ]
+face_selector_races : List[Race] = [ 'white', 'black', 'latino', 'asian', 'indian', 'arabic' ]
+face_occluder_models : List[FaceOccluderModel] = [ 'xseg_1', 'xseg_2', 'xseg_3' ]
+face_parser_models : List[FaceParserModel] = [ 'bisenet_resnet_18', 'bisenet_resnet_34' ]
+face_mask_types : List[FaceMaskType] = [ 'box', 'occlusion', 'area', 'region' ]
+face_mask_area_set : FaceMaskAreaSet =\
+{
+	'upper-face': [ 0, 1, 2, 31, 32, 33, 34, 35, 14, 15, 16, 26, 25, 24, 23, 22, 21, 20, 19, 18, 17 ],
+	'lower-face': [ 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 35, 34, 33, 32, 31 ],
+	'mouth': [ 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67 ]
+}
+face_mask_region_set : FaceMaskRegionSet =\
+{
+	'skin': 1,
+	'left-eyebrow': 2,
+	'right-eyebrow': 3,
+	'left-eye': 4,
+	'right-eye': 5,
+	'glasses': 6,
+	'nose': 10,
+	'mouth': 11,
+	'upper-lip': 12,
+	'lower-lip': 13
+}
+face_mask_areas : List[FaceMaskArea] = list(face_mask_area_set.keys())
+face_mask_regions : List[FaceMaskRegion] = list(face_mask_region_set.keys())
+
+audio_type_set : AudioTypeSet =\
+{
+	'flac': 'audio/flac',
+	'm4a': 'audio/mp4',
+	'mp3': 'audio/mpeg',
+	'ogg': 'audio/ogg',
+	'opus': 'audio/opus',
+	'wav': 'audio/x-wav'
+}
+image_type_set : ImageTypeSet =\
+{
+	'bmp': 'image/bmp',
+	'jpeg': 'image/jpeg',
+	'png': 'image/png',
+	'tiff': 'image/tiff',
+	'webp': 'image/webp'
+}
+video_type_set : VideoTypeSet =\
+{
+	'avi': 'video/x-msvideo',
+	'm4v': 'video/mp4',
+	'mkv': 'video/x-matroska',
+	'mp4': 'video/mp4',
+	'mov': 'video/quicktime',
+	'webm': 'video/webm'
+}
+audio_formats : List[AudioFormat] = list(audio_type_set.keys())
+image_formats : List[ImageFormat] = list(image_type_set.keys())
+video_formats : List[VideoFormat] = list(video_type_set.keys())
+temp_frame_formats : List[TempFrameFormat] = [ 'bmp', 'jpeg', 'png', 'tiff' ]
+
+output_encoder_set : EncoderSet =\
+{
+	'audio': [ 'flac', 'aac', 'libmp3lame', 'libopus', 'libvorbis', 'pcm_s16le', 'pcm_s32le' ],
+	'video': [ 'libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf', 'h264_qsv', 'hevc_qsv', 'h264_videotoolbox', 'hevc_videotoolbox', 'rawvideo' ]
+}
+output_audio_encoders : List[AudioEncoder] = output_encoder_set.get('audio')
+output_video_encoders : List[VideoEncoder] = output_encoder_set.get('video')
+output_video_presets : List[VideoPreset] = [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]
 
 image_template_sizes : List[float] = [ 0.25, 0.5, 0.75, 1, 1.5, 2, 2.5, 3, 3.5, 4 ]
 video_template_sizes : List[int] = [ 240, 360, 480, 540, 720, 1080, 1440, 2160, 4320 ]
 
+benchmark_set : BenchmarkSet =\
+{
+	'240p': '.assets/examples/target-240p.mp4',
+	'360p': '.assets/examples/target-360p.mp4',
+	'540p': '.assets/examples/target-540p.mp4',
+	'720p': '.assets/examples/target-720p.mp4',
+	'1080p': '.assets/examples/target-1080p.mp4',
+	'1440p': '.assets/examples/target-1440p.mp4',
+	'2160p': '.assets/examples/target-2160p.mp4'
+}
+benchmark_resolutions : List[BenchmarkResolution] = list(benchmark_set.keys())
+
+webcam_modes : List[WebcamMode] = [ 'inline', 'udp', 'v4l2' ]
+webcam_resolutions : List[str] = [ '320x240', '640x480', '800x600', '1024x768', '1280x720', '1280x960', '1920x1080', '2560x1440', '3840x2160' ]
+
+execution_provider_set : ExecutionProviderSet =\
+{
+	'cuda': 'CUDAExecutionProvider',
+	'tensorrt': 'TensorrtExecutionProvider',
+	'directml': 'DmlExecutionProvider',
+	'rocm': 'ROCMExecutionProvider',
+	'openvino': 'OpenVINOExecutionProvider',
+	'coreml': 'CoreMLExecutionProvider',
+	'cpu': 'CPUExecutionProvider'
+}
+execution_providers : List[ExecutionProvider] = list(execution_provider_set.keys())
+download_provider_set : DownloadProviderSet =\
+{
+	'github':
+	{
+		'urls':
+		[
+			'https://github.com'
+		],
+		'path': '/facefusion/facefusion-assets/releases/download/{base_name}/{file_name}'
+	},
+	'huggingface':
+	{
+		'urls':
+		[
+			'https://huggingface.co',
+			'https://hf-mirror.com'
+		],
+		'path': '/facefusion/{base_name}/resolve/main/{file_name}'
+	}
+}
+download_providers : List[DownloadProvider] = list(download_provider_set.keys())
+download_scopes : List[DownloadScope] = [ 'lite', 'full' ]
+
+video_memory_strategies : List[VideoMemoryStrategy] = [ 'strict', 'moderate', 'tolerant' ]
+
 log_level_set : LogLevelSet =\
 {
 	'error': logging.ERROR,
@@ -35,21 +143,12 @@ log_level_set : LogLevelSet =\
 	'info': logging.INFO,
 	'debug': logging.DEBUG
 }
-
-execution_provider_set : ExecutionProviderSet =\
-{
-	'cpu': 'CPUExecutionProvider',
-	'coreml': 'CoreMLExecutionProvider',
-	'cuda': 'CUDAExecutionProvider',
-	'directml': 'DmlExecutionProvider',
-	'openvino': 'OpenVINOExecutionProvider',
-	'rocm': 'ROCMExecutionProvider',
-	'tensorrt': 'TensorrtExecutionProvider'
-}
+log_levels : List[LogLevel] = list(log_level_set.keys())
 
 ui_workflows : List[UiWorkflow] = [ 'instant_runner', 'job_runner', 'job_manager' ]
 job_statuses : List[JobStatus] = [ 'drafted', 'queued', 'completed', 'failed' ]
 
+benchmark_cycle_count_range : Sequence[int] = create_int_range(1, 10, 1)
 execution_thread_count_range : Sequence[int] = create_int_range(1, 32, 1)
 execution_queue_count_range : Sequence[int] = create_int_range(1, 4, 1)
 system_memory_limit_range : Sequence[int] = create_int_range(0, 128, 4)
@@ -59,6 +158,8 @@ face_landmarker_score_range : Sequence[Score] = create_float_range(0.0, 1.0, 0.0
 face_mask_blur_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
 face_mask_padding_range : Sequence[int] = create_int_range(0, 100, 1)
 face_selector_age_range : Sequence[int] = create_int_range(0, 100, 1)
-reference_face_distance_range : Sequence[float] = create_float_range(0.0, 1.5, 0.05)
+reference_face_distance_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
 output_image_quality_range : Sequence[int] = create_int_range(0, 100, 1)
+output_audio_quality_range : Sequence[int] = create_int_range(0, 100, 1)
+output_audio_volume_range : Sequence[int] = create_int_range(0, 100, 1)
 output_video_quality_range : Sequence[int] = create_int_range(0, 100, 1)

facefusion/cli_helper.py

@@ -0,0 +1,35 @@
+from typing import Tuple
+
+from facefusion.logger import get_package_logger
+from facefusion.types import TableContents, TableHeaders
+
+
+def render_table(headers : TableHeaders, contents : TableContents) -> None:
+	package_logger = get_package_logger()
+	table_column, table_separator = create_table_parts(headers, contents)
+
+	package_logger.critical(table_separator)
+	package_logger.critical(table_column.format(*headers))
+	package_logger.critical(table_separator)
+
+	for content in contents:
+		content = [ str(value) for value in content ]
+		package_logger.critical(table_column.format(*content))
+
+	package_logger.critical(table_separator)
+
+
+def create_table_parts(headers : TableHeaders, contents : TableContents) -> Tuple[str, str]:
+	column_parts = []
+	separator_parts = []
+	widths = [ len(header) for header in headers ]
+
+	for content in contents:
+		for index, value in enumerate(content):
+			widths[index] = max(widths[index], len(str(value)))
+
+	for width in widths:
+		column_parts.append('{:<' + str(width) + '}')
+		separator_parts.append('-' * width)
+
+	return '| ' + ' | '.join(column_parts) + ' |', '+-' + '-+-'.join(separator_parts) + '-+'

facefusion/common_helper.py

@@ -1,5 +1,5 @@
 import platform
-from typing import Any, Optional, Sequence
+from typing import Any, Iterable, Optional, Reversible, Sequence
 
 
 def is_linux() -> bool:
@@ -50,23 +50,35 @@ def calc_float_step(float_range : Sequence[float]) -> float:
 	return round(float_range[1] - float_range[0], 2)
 
 
-def cast_int(value : Any) -> Optional[Any]:
+def cast_int(value : Any) -> Optional[int]:
 	try:
 		return int(value)
 	except (ValueError, TypeError):
 		return None
 
 
-def cast_float(value : Any) -> Optional[Any]:
+def cast_float(value : Any) -> Optional[float]:
 	try:
 		return float(value)
 	except (ValueError, TypeError):
 		return None
 
 
+def cast_bool(value : Any) -> Optional[bool]:
+	if value == 'True':
+		return True
+	if value == 'False':
+		return False
+	return None
+
+
 def get_first(__list__ : Any) -> Any:
-	return next(iter(__list__), None)
+	if isinstance(__list__, Iterable):
+		return next(iter(__list__), None)
+	return None
 
 
 def get_last(__list__ : Any) -> Any:
-	return next(reversed(__list__), None)
+	if isinstance(__list__, Reversible):
+		return next(reversed(__list__), None)
+	return None

facefusion/config.py

@@ -1,92 +1,74 @@
 from configparser import ConfigParser
-from typing import Any, List, Optional
+from typing import List, Optional
 
 from facefusion import state_manager
-from facefusion.common_helper import cast_float, cast_int
+from facefusion.common_helper import cast_bool, cast_float, cast_int
 
-CONFIG = None
+CONFIG_PARSER = None
 
 
-def get_config() -> ConfigParser:
-	global CONFIG
+def get_config_parser() -> ConfigParser:
+	global CONFIG_PARSER
 
-	if CONFIG is None:
-		CONFIG = ConfigParser()
-		CONFIG.read(state_manager.get_item('config_path'), encoding = 'utf-8')
-	return CONFIG
+	if CONFIG_PARSER is None:
+		CONFIG_PARSER = ConfigParser()
+		CONFIG_PARSER.read(state_manager.get_item('config_path'), encoding = 'utf-8')
+	return CONFIG_PARSER
 
 
-def clear_config() -> None:
-	global CONFIG
+def clear_config_parser() -> None:
+	global CONFIG_PARSER
 
-	CONFIG = None
+	CONFIG_PARSER = None
 
 
-def get_str_value(key : str, fallback : Optional[str] = None) -> Optional[str]:
-	value = get_value_by_notation(key)
+def get_str_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[str]:
+	config_parser = get_config_parser()
 
-	if value or fallback:
-		return str(value or fallback)
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.get(section, option)
+	return fallback
+
+
+def get_int_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[int]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.getint(section, option)
+	return cast_int(fallback)
+
+
+def get_float_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[float]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.getfloat(section, option)
+	return cast_float(fallback)
+
+
+def get_bool_value(section : str, option : str, fallback : Optional[str] = None) -> Optional[bool]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.getboolean(section, option)
+	return cast_bool(fallback)
+
+
+def get_str_list(section : str, option : str, fallback : Optional[str] = None) -> Optional[List[str]]:
+	config_parser = get_config_parser()
+
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return config_parser.get(section, option).split()
+	if fallback:
+		return fallback.split()
 	return None
 
 
-def get_int_value(key : str, fallback : Optional[str] = None) -> Optional[int]:
-	value = get_value_by_notation(key)
+def get_int_list(section : str, option : str, fallback : Optional[str] = None) -> Optional[List[int]]:
+	config_parser = get_config_parser()
 
-	if value or fallback:
-		return cast_int(value or fallback)
-	return None
-
-
-def get_float_value(key : str, fallback : Optional[str] = None) -> Optional[float]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return cast_float(value or fallback)
-	return None
-
-
-def get_bool_value(key : str, fallback : Optional[str] = None) -> Optional[bool]:
-	value = get_value_by_notation(key)
-
-	if value == 'True' or fallback == 'True':
-		return True
-	if value == 'False' or fallback == 'False':
-		return False
-	return None
-
-
-def get_str_list(key : str, fallback : Optional[str] = None) -> Optional[List[str]]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return [ str(value) for value in (value or fallback).split(' ') ]
-	return None
-
-
-def get_int_list(key : str, fallback : Optional[str] = None) -> Optional[List[int]]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return [ cast_int(value) for value in (value or fallback).split(' ') ]
-	return None
-
-
-def get_float_list(key : str, fallback : Optional[str] = None) -> Optional[List[float]]:
-	value = get_value_by_notation(key)
-
-	if value or fallback:
-		return [ cast_float(value) for value in (value or fallback).split(' ') ]
-	return None
-
-
-def get_value_by_notation(key : str) -> Optional[Any]:
-	config = get_config()
-
-	if '.' in key:
-		section, name = key.split('.')
-		if section in config and name in config[section]:
-			return config[section][name]
-	if key in config:
-		return config[key]
+	if config_parser.has_option(section, option) and config_parser.get(section, option).strip():
+		return list(map(int, config_parser.get(section, option).split()))
+	if fallback:
+		return list(map(int, fallback.split()))
 	return None

facefusion/content_analyser.py

@@ -1,64 +1,127 @@
 from functools import lru_cache
+from typing import List, Tuple
 
-import cv2
 import numpy
 from tqdm import tqdm
 
 from facefusion import inference_manager, state_manager, wording
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
+from facefusion.execution import has_execution_provider
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import Fps, InferencePool, ModelOptions, ModelSet, VisionFrame
-from facefusion.vision import count_video_frame_total, detect_video_fps, get_video_frame, read_image
+from facefusion.types import Detection, DownloadScope, DownloadSet, ExecutionProvider, Fps, InferencePool, ModelSet, VisionFrame
+from facefusion.vision import detect_video_fps, fit_frame, read_image, read_video_frame
 
-MODEL_SET : ModelSet =\
-{
-	'open_nsfw':
-	{
-		'hashes':
-		{
-			'content_analyser':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/open_nsfw.hash',
-				'path': resolve_relative_path('../.assets/models/open_nsfw.hash')
-			}
-		},
-		'sources':
-		{
-			'content_analyser':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/open_nsfw.onnx',
-				'path': resolve_relative_path('../.assets/models/open_nsfw.onnx')
-			}
-		},
-		'size': (224, 224),
-		'mean': [ 104, 117, 123 ]
-	}
-}
-PROBABILITY_LIMIT = 0.80
-RATE_LIMIT = 10
 STREAM_COUNTER = 0
 
 
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
+	{
+		'nsfw_1':
+		{
+			'hashes':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_1.hash'),
+					'path': resolve_relative_path('../.assets/models/nsfw_1.hash')
+				}
+			},
+			'sources':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_1.onnx'),
+					'path': resolve_relative_path('../.assets/models/nsfw_1.onnx')
+				}
+			},
+			'size': (640, 640),
+			'mean': (0.0, 0.0, 0.0),
+			'standard_deviation': (1.0, 1.0, 1.0)
+		},
+		'nsfw_2':
+		{
+			'hashes':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_2.hash'),
+					'path': resolve_relative_path('../.assets/models/nsfw_2.hash')
+				}
+			},
+			'sources':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_2.onnx'),
+					'path': resolve_relative_path('../.assets/models/nsfw_2.onnx')
+				}
+			},
+			'size': (384, 384),
+			'mean': (0.5, 0.5, 0.5),
+			'standard_deviation': (0.5, 0.5, 0.5)
+		},
+		'nsfw_3':
+		{
+			'hashes':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_3.hash'),
+					'path': resolve_relative_path('../.assets/models/nsfw_3.hash')
+				}
+			},
+			'sources':
+			{
+				'content_analyser':
+				{
+					'url': resolve_download_url('models-3.3.0', 'nsfw_3.onnx'),
+					'path': resolve_relative_path('../.assets/models/nsfw_3.onnx')
+				}
+			},
+			'size': (448, 448),
+			'mean': (0.48145466, 0.4578275, 0.40821073),
+			'standard_deviation': (0.26862954, 0.26130258, 0.27577711)
+		}
+	}
+
+
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ 'nsfw_1', 'nsfw_2', 'nsfw_3' ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ 'nsfw_1', 'nsfw_2', 'nsfw_3' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
-def get_model_options() -> ModelOptions:
-	return MODEL_SET.get('open_nsfw')
+def resolve_execution_providers() -> List[ExecutionProvider]:
+	if has_execution_provider('coreml'):
+		return [ 'cpu' ]
+	return state_manager.get_item('execution_providers')
+
+
+def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
+	model_set = create_static_model_set('full')
+	model_hash_set = {}
+	model_source_set = {}
+
+	for content_analyser_model in [ 'nsfw_1', 'nsfw_2', 'nsfw_3' ]:
+		model_hash_set[content_analyser_model] = model_set.get(content_analyser_model).get('hashes').get('content_analyser')
+		model_source_set[content_analyser_model] = model_set.get(content_analyser_model).get('sources').get('content_analyser')
+
+	return model_hash_set, model_source_set
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set, model_source_set = collect_model_downloads()
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def analyse_stream(vision_frame : VisionFrame, video_fps : Fps) -> bool:
@@ -71,54 +134,92 @@ def analyse_stream(vision_frame : VisionFrame, video_fps : Fps) -> bool:
 
 
 def analyse_frame(vision_frame : VisionFrame) -> bool:
-	vision_frame = prepare_frame(vision_frame)
-	probability = forward(vision_frame)
-
-	return probability > PROBABILITY_LIMIT
-
-
-def forward(vision_frame : VisionFrame) -> float:
-	content_analyser = get_inference_pool().get('content_analyser')
-
-	with conditional_thread_semaphore():
-		probability = content_analyser.run(None,
-		{
-			'input': vision_frame
-		})[0][0][1]
-
-	return probability
-
-
-def prepare_frame(vision_frame : VisionFrame) -> VisionFrame:
-	model_size = get_model_options().get('size')
-	model_mean = get_model_options().get('mean')
-	vision_frame = cv2.resize(vision_frame, model_size).astype(numpy.float32)
-	vision_frame -= numpy.array(model_mean).astype(numpy.float32)
-	vision_frame = numpy.expand_dims(vision_frame, axis = 0)
-	return vision_frame
+	return detect_nsfw(vision_frame)
 
 
 @lru_cache(maxsize = None)
 def analyse_image(image_path : str) -> bool:
-	frame = read_image(image_path)
-	return analyse_frame(frame)
+	vision_frame = read_image(image_path)
+	return analyse_frame(vision_frame)
 
 
 @lru_cache(maxsize = None)
-def analyse_video(video_path : str, start_frame : int, end_frame : int) -> bool:
-	video_frame_total = count_video_frame_total(video_path)
+def analyse_video(video_path : str, trim_frame_start : int, trim_frame_end : int) -> bool:
 	video_fps = detect_video_fps(video_path)
-	frame_range = range(start_frame or 0, end_frame or video_frame_total)
+	frame_range = range(trim_frame_start, trim_frame_end)
 	rate = 0.0
+	total = 0
 	counter = 0
 
 	with tqdm(total = len(frame_range), desc = wording.get('analysing'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+
 		for frame_number in frame_range:
 			if frame_number % int(video_fps) == 0:
-				frame = get_video_frame(video_path, frame_number)
-				if analyse_frame(frame):
+				vision_frame = read_video_frame(video_path, frame_number)
+				total += 1
+				if analyse_frame(vision_frame):
 					counter += 1
-			rate = counter * int(video_fps) / len(frame_range) * 100
-			progress.update()
+			if counter > 0 and total > 0:
+				rate = counter / total * 100
 			progress.set_postfix(rate = rate)
-	return rate > RATE_LIMIT
+			progress.update()
+
+	return bool(rate > 10.0)
+
+
+def detect_nsfw(vision_frame : VisionFrame) -> bool:
+	is_nsfw_1 = detect_with_nsfw_1(vision_frame)
+	is_nsfw_2 = detect_with_nsfw_2(vision_frame)
+	is_nsfw_3 = detect_with_nsfw_3(vision_frame)
+
+	return is_nsfw_1 and is_nsfw_2 or is_nsfw_1 and is_nsfw_3 or is_nsfw_2 and is_nsfw_3
+
+
+def detect_with_nsfw_1(vision_frame : VisionFrame) -> bool:
+	detect_vision_frame = prepare_detect_frame(vision_frame, 'nsfw_1')
+	detection = forward_nsfw(detect_vision_frame, 'nsfw_1')
+	detection_score = numpy.max(numpy.amax(detection[:, 4:], axis = 1))
+	return bool(detection_score > 0.2)
+
+
+def detect_with_nsfw_2(vision_frame : VisionFrame) -> bool:
+	detect_vision_frame = prepare_detect_frame(vision_frame, 'nsfw_2')
+	detection = forward_nsfw(detect_vision_frame, 'nsfw_2')
+	detection_score = detection[0] - detection[1]
+	return bool(detection_score > 0.25)
+
+
+def detect_with_nsfw_3(vision_frame : VisionFrame) -> bool:
+	detect_vision_frame = prepare_detect_frame(vision_frame, 'nsfw_3')
+	detection = forward_nsfw(detect_vision_frame, 'nsfw_3')
+	detection_score = (detection[2] + detection[3]) - (detection[0] + detection[1])
+	return bool(detection_score > 10.5)
+
+
+def forward_nsfw(vision_frame : VisionFrame, nsfw_model : str) -> Detection:
+	content_analyser = get_inference_pool().get(nsfw_model)
+
+	with conditional_thread_semaphore():
+		detection = content_analyser.run(None,
+		{
+			'input': vision_frame
+		})[0]
+
+	if nsfw_model in [ 'nsfw_2', 'nsfw_3' ]:
+		return detection[0]
+
+	return detection
+
+
+def prepare_detect_frame(temp_vision_frame : VisionFrame, model_name : str) -> VisionFrame:
+	model_set = create_static_model_set('full').get(model_name)
+	model_size = model_set.get('size')
+	model_mean = model_set.get('mean')
+	model_standard_deviation = model_set.get('standard_deviation')
+
+	detect_vision_frame = fit_frame(temp_vision_frame, model_size)
+	detect_vision_frame = detect_vision_frame[:, :, ::-1] / 255.0
+	detect_vision_frame -= model_mean
+	detect_vision_frame /= model_standard_deviation
+	detect_vision_frame = numpy.expand_dims(detect_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
+	return detect_vision_frame

facefusion/core.py

@@ -1,3 +1,5 @@
+import inspect
+import itertools
 import shutil
 import signal
 import sys
@@ -5,72 +7,92 @@ from time import time
 
 import numpy
 
-from facefusion import content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, logger, process_manager, state_manager, voice_extractor, wording
-from facefusion.args import apply_args, collect_job_args, reduce_step_args
+from facefusion import benchmarker, cli_helper, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, hash_helper, logger, process_manager, state_manager, video_manager, voice_extractor, wording
+from facefusion.args import apply_args, collect_job_args, reduce_job_args, reduce_step_args
 from facefusion.common_helper import get_first
 from facefusion.content_analyser import analyse_image, analyse_video
 from facefusion.download import conditional_download_hashes, conditional_download_sources
-from facefusion.exit_helper import conditional_exit, graceful_exit, hard_exit
+from facefusion.exit_helper import hard_exit, signal_exit
 from facefusion.face_analyser import get_average_face, get_many_faces, get_one_face
 from facefusion.face_selector import sort_and_filter_faces
 from facefusion.face_store import append_reference_face, clear_reference_faces, get_reference_faces
 from facefusion.ffmpeg import copy_image, extract_frames, finalize_image, merge_video, replace_audio, restore_audio
-from facefusion.filesystem import filter_audio_paths, is_image, is_video, list_directory, resolve_relative_path
+from facefusion.filesystem import filter_audio_paths, get_file_name, is_image, is_video, resolve_file_paths, resolve_file_pattern
 from facefusion.jobs import job_helper, job_manager, job_runner
 from facefusion.jobs.job_list import compose_job_list
 from facefusion.memory import limit_system_memory
 from facefusion.processors.core import get_processors_modules
 from facefusion.program import create_program
 from facefusion.program_helper import validate_args
-from facefusion.statistics import conditional_log_statistics
-from facefusion.temp_helper import clear_temp_directory, create_temp_directory, get_temp_file_path, get_temp_frame_paths, move_temp_file
-from facefusion.typing import Args, ErrorCode
-from facefusion.vision import get_video_frame, pack_resolution, read_image, read_static_images, restrict_image_resolution, restrict_video_fps, restrict_video_resolution, unpack_resolution
+from facefusion.temp_helper import clear_temp_directory, create_temp_directory, get_temp_file_path, move_temp_file, resolve_temp_frame_paths
+from facefusion.types import Args, ErrorCode
+from facefusion.vision import pack_resolution, read_image, read_static_images, read_video_frame, restrict_image_resolution, restrict_trim_frame, restrict_video_fps, restrict_video_resolution, unpack_resolution
 
 
 def cli() -> None:
-	signal.signal(signal.SIGINT, lambda signal_number, frame: graceful_exit(0))
-	program = create_program()
+	if pre_check():
+		signal.signal(signal.SIGINT, signal_exit)
+		program = create_program()
 
-	if validate_args(program):
-		args = vars(program.parse_args())
-		apply_args(args, state_manager.init_item)
+		if validate_args(program):
+			args = vars(program.parse_args())
+			apply_args(args, state_manager.init_item)
 
-		if state_manager.get_item('command'):
-			logger.init(state_manager.get_item('log_level'))
-			route(args)
+			if state_manager.get_item('command'):
+				logger.init(state_manager.get_item('log_level'))
+				route(args)
+			else:
+				program.print_help()
 		else:
-			program.print_help()
+			hard_exit(2)
+	else:
+		hard_exit(2)
 
 
 def route(args : Args) -> None:
 	system_memory_limit = state_manager.get_item('system_memory_limit')
+
 	if system_memory_limit and system_memory_limit > 0:
 		limit_system_memory(system_memory_limit)
+
 	if state_manager.get_item('command') == 'force-download':
 		error_code = force_download()
-		return conditional_exit(error_code)
+		return hard_exit(error_code)
+
+	if state_manager.get_item('command') == 'benchmark':
+		if not common_pre_check() or not processors_pre_check() or not benchmarker.pre_check():
+			return hard_exit(2)
+		benchmarker.render()
+
 	if state_manager.get_item('command') in [ 'job-list', 'job-create', 'job-submit', 'job-submit-all', 'job-delete', 'job-delete-all', 'job-add-step', 'job-remix-step', 'job-insert-step', 'job-remove-step' ]:
 		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
 			hard_exit(1)
 		error_code = route_job_manager(args)
 		hard_exit(error_code)
-	if not pre_check():
-		return conditional_exit(2)
+
 	if state_manager.get_item('command') == 'run':
 		import facefusion.uis.core as ui
 
 		if not common_pre_check() or not processors_pre_check():
-			return conditional_exit(2)
+			return hard_exit(2)
 		for ui_layout in ui.get_ui_layouts_modules(state_manager.get_item('ui_layouts')):
 			if not ui_layout.pre_check():
-				return conditional_exit(2)
+				return hard_exit(2)
+		ui.init()
 		ui.launch()
+
 	if state_manager.get_item('command') == 'headless-run':
 		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
 			hard_exit(1)
 		error_core = process_headless(args)
 		hard_exit(error_core)
+
+	if state_manager.get_item('command') == 'batch-run':
+		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
+			hard_exit(1)
+		error_core = process_batch(args)
+		hard_exit(error_core)
+
 	if state_manager.get_item('command') in [ 'job-run', 'job-run-all', 'job-retry', 'job-retry-all' ]:
 		if not job_manager.init_jobs(state_manager.get_item('jobs_path')):
 			hard_exit(1)
@@ -79,12 +101,14 @@ def route(args : Args) -> None:
 
 
 def pre_check() -> bool:
-	if sys.version_info < (3, 9):
-		logger.error(wording.get('python_not_supported').format(version = '3.9'), __name__)
+	if sys.version_info < (3, 10):
+		logger.error(wording.get('python_not_supported').format(version = '3.10'), __name__)
 		return False
+
 	if not shutil.which('curl'):
 		logger.error(wording.get('curl_not_installed'), __name__)
 		return False
+
 	if not shutil.which('ffmpeg'):
 		logger.error(wording.get('ffmpeg_not_installed'), __name__)
 		return False
@@ -92,7 +116,7 @@ def pre_check() -> bool:
 
 
 def common_pre_check() -> bool:
-	modules =\
+	common_modules =\
 	[
 		content_analyser,
 		face_classifier,
@@ -103,7 +127,10 @@ def common_pre_check() -> bool:
 		voice_extractor
 	]
 
-	return all(module.pre_check() for module in modules)
+	content_analyser_content = inspect.getsource(content_analyser).encode()
+	is_valid = hash_helper.create_hash(content_analyser_content) == 'b159fd9d'
+
+	return all(module.pre_check() for module in common_modules) and is_valid
 
 
 def processors_pre_check() -> bool:
@@ -113,64 +140,28 @@ def processors_pre_check() -> bool:
 	return True
 
 
-def conditional_process() -> ErrorCode:
-	start_time = time()
-	for processor_module in get_processors_modules(state_manager.get_item('processors')):
-		if not processor_module.pre_process('output'):
-			return 2
-	conditional_append_reference_faces()
-	if is_image(state_manager.get_item('target_path')):
-		return process_image(start_time)
-	if is_video(state_manager.get_item('target_path')):
-		return process_video(start_time)
-	return 0
-
-
-def conditional_append_reference_faces() -> None:
-	if 'reference' in state_manager.get_item('face_selector_mode') and not get_reference_faces():
-		source_frames = read_static_images(state_manager.get_item('source_paths'))
-		source_faces = get_many_faces(source_frames)
-		source_face = get_average_face(source_faces)
-		if is_video(state_manager.get_item('target_path')):
-			reference_frame = get_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
-		else:
-			reference_frame = read_image(state_manager.get_item('target_path'))
-		reference_faces = sort_and_filter_faces(get_many_faces([ reference_frame ]))
-		reference_face = get_one_face(reference_faces, state_manager.get_item('reference_face_position'))
-		append_reference_face('origin', reference_face)
-
-		if source_face and reference_face:
-			for processor_module in get_processors_modules(state_manager.get_item('processors')):
-				abstract_reference_frame = processor_module.get_reference_frame(source_face, reference_face, reference_frame)
-				if numpy.any(abstract_reference_frame):
-					abstract_reference_faces = sort_and_filter_faces(get_many_faces([ abstract_reference_frame ]))
-					abstract_reference_face = get_one_face(abstract_reference_faces, state_manager.get_item('reference_face_position'))
-					append_reference_face(processor_module.__name__, abstract_reference_face)
-
-
 def force_download() -> ErrorCode:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	available_processors = list_directory('facefusion/processors/modules')
 	common_modules =\
 	[
 		content_analyser,
 		face_classifier,
 		face_detector,
 		face_landmarker,
-		face_recognizer,
 		face_masker,
+		face_recognizer,
 		voice_extractor
 	]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	processor_modules = get_processors_modules(available_processors)
 
 	for module in common_modules + processor_modules:
-		if hasattr(module, 'MODEL_SET'):
-			for model in module.MODEL_SET.values():
-				model_hashes = model.get('hashes')
-				model_sources = model.get('sources')
+		if hasattr(module, 'create_static_model_set'):
+			for model in module.create_static_model_set(state_manager.get_item('download_scope')).values():
+				model_hash_set = model.get('hashes')
+				model_source_set = model.get('sources')
 
-				if model_hashes and model_sources:
-					if not conditional_download_hashes(download_directory_path, model_hashes) or not conditional_download_sources(download_directory_path, model_sources):
+				if model_hash_set and model_source_set:
+					if not conditional_download_hashes(model_hash_set) or not conditional_download_sources(model_source_set):
 						return 1
 
 	return 0
@@ -181,39 +172,45 @@ def route_job_manager(args : Args) -> ErrorCode:
 		job_headers, job_contents = compose_job_list(state_manager.get_item('job_status'))
 
 		if job_contents:
-			logger.table(job_headers, job_contents)
+			cli_helper.render_table(job_headers, job_contents)
 			return 0
 		return 1
+
 	if state_manager.get_item('command') == 'job-create':
 		if job_manager.create_job(state_manager.get_item('job_id')):
 			logger.info(wording.get('job_created').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.error(wording.get('job_not_created').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-submit':
 		if job_manager.submit_job(state_manager.get_item('job_id')):
 			logger.info(wording.get('job_submitted').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.error(wording.get('job_not_submitted').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-submit-all':
-		if job_manager.submit_jobs():
+		if job_manager.submit_jobs(state_manager.get_item('halt_on_error')):
 			logger.info(wording.get('job_all_submitted'), __name__)
 			return 0
 		logger.error(wording.get('job_all_not_submitted'), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-delete':
 		if job_manager.delete_job(state_manager.get_item('job_id')):
 			logger.info(wording.get('job_deleted').format(job_id = state_manager.get_item('job_id')), __name__)
 			return 0
 		logger.error(wording.get('job_not_deleted').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-delete-all':
-		if job_manager.delete_jobs():
+		if job_manager.delete_jobs(state_manager.get_item('halt_on_error')):
 			logger.info(wording.get('job_all_deleted'), __name__)
 			return 0
 		logger.error(wording.get('job_all_not_deleted'), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-add-step':
 		step_args = reduce_step_args(args)
 
@@ -222,6 +219,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 			return 0
 		logger.error(wording.get('job_step_not_added').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-remix-step':
 		step_args = reduce_step_args(args)
 
@@ -230,6 +228,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 			return 0
 		logger.error(wording.get('job_remix_step_not_added').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-insert-step':
 		step_args = reduce_step_args(args)
 
@@ -238,6 +237,7 @@ def route_job_manager(args : Args) -> ErrorCode:
 			return 0
 		logger.error(wording.get('job_step_not_inserted').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-remove-step':
 		if job_manager.remove_step(state_manager.get_item('job_id'), state_manager.get_item('step_index')):
 			logger.info(wording.get('job_step_removed').format(job_id = state_manager.get_item('job_id'), step_index = state_manager.get_item('step_index')), __name__)
@@ -255,13 +255,15 @@ def route_job_runner() -> ErrorCode:
 			return 0
 		logger.info(wording.get('processing_job_failed').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-run-all':
 		logger.info(wording.get('running_jobs'), __name__)
-		if job_runner.run_jobs(process_step):
+		if job_runner.run_jobs(process_step, state_manager.get_item('halt_on_error')):
 			logger.info(wording.get('processing_jobs_succeed'), __name__)
 			return 0
 		logger.info(wording.get('processing_jobs_failed'), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-retry':
 		logger.info(wording.get('retrying_job').format(job_id = state_manager.get_item('job_id')), __name__)
 		if job_runner.retry_job(state_manager.get_item('job_id'), process_step):
@@ -269,9 +271,10 @@ def route_job_runner() -> ErrorCode:
 			return 0
 		logger.info(wording.get('processing_job_failed').format(job_id = state_manager.get_item('job_id')), __name__)
 		return 1
+
 	if state_manager.get_item('command') == 'job-retry-all':
 		logger.info(wording.get('retrying_jobs'), __name__)
-		if job_runner.retry_jobs(process_step):
+		if job_runner.retry_jobs(process_step, state_manager.get_item('halt_on_error')):
 			logger.info(wording.get('processing_jobs_succeed'), __name__)
 			return 0
 		logger.info(wording.get('processing_jobs_failed'), __name__)
@@ -279,6 +282,44 @@ def route_job_runner() -> ErrorCode:
 	return 2
 
 
+def process_headless(args : Args) -> ErrorCode:
+	job_id = job_helper.suggest_job_id('headless')
+	step_args = reduce_step_args(args)
+
+	if job_manager.create_job(job_id) and job_manager.add_step(job_id, step_args) and job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step):
+		return 0
+	return 1
+
+
+def process_batch(args : Args) -> ErrorCode:
+	job_id = job_helper.suggest_job_id('batch')
+	step_args = reduce_step_args(args)
+	job_args = reduce_job_args(args)
+	source_paths = resolve_file_pattern(job_args.get('source_pattern'))
+	target_paths = resolve_file_pattern(job_args.get('target_pattern'))
+
+	if job_manager.create_job(job_id):
+		if source_paths and target_paths:
+			for index, (source_path, target_path) in enumerate(itertools.product(source_paths, target_paths)):
+				step_args['source_paths'] = [ source_path ]
+				step_args['target_path'] = target_path
+				step_args['output_path'] = job_args.get('output_pattern').format(index = index)
+				if not job_manager.add_step(job_id, step_args):
+					return 1
+			if job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step):
+				return 0
+
+		if not source_paths and target_paths:
+			for index, target_path in enumerate(target_paths):
+				step_args['target_path'] = target_path
+				step_args['output_path'] = job_args.get('output_pattern').format(index = index)
+				if not job_manager.add_step(job_id, step_args):
+					return 1
+			if job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step):
+				return 0
+	return 1
+
+
 def process_step(job_id : str, step_index : int, step_args : Args) -> bool:
 	clear_reference_faces()
 	step_total = job_manager.count_step_total(job_id)
@@ -292,25 +333,54 @@ def process_step(job_id : str, step_index : int, step_args : Args) -> bool:
 	return False
 
 
-def process_headless(args : Args) -> ErrorCode:
-	job_id = job_helper.suggest_job_id('headless')
-	step_args = reduce_step_args(args)
+def conditional_process() -> ErrorCode:
+	start_time = time()
 
-	if job_manager.create_job(job_id) and job_manager.add_step(job_id, step_args) and job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step):
-		return 0
-	return 1
+	for processor_module in get_processors_modules(state_manager.get_item('processors')):
+		if not processor_module.pre_process('output'):
+			return 2
+
+	conditional_append_reference_faces()
+
+	if is_image(state_manager.get_item('target_path')):
+		return process_image(start_time)
+	if is_video(state_manager.get_item('target_path')):
+		return process_video(start_time)
+
+	return 0
+
+
+def conditional_append_reference_faces() -> None:
+	if 'reference' in state_manager.get_item('face_selector_mode') and not get_reference_faces():
+		source_frames = read_static_images(state_manager.get_item('source_paths'))
+		source_faces = get_many_faces(source_frames)
+		source_face = get_average_face(source_faces)
+		if is_video(state_manager.get_item('target_path')):
+			reference_frame = read_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
+		else:
+			reference_frame = read_image(state_manager.get_item('target_path'))
+		reference_faces = sort_and_filter_faces(get_many_faces([ reference_frame ]))
+		reference_face = get_one_face(reference_faces, state_manager.get_item('reference_face_position'))
+		append_reference_face('origin', reference_face)
+
+		if source_face and reference_face:
+			for processor_module in get_processors_modules(state_manager.get_item('processors')):
+				abstract_reference_frame = processor_module.get_reference_frame(source_face, reference_face, reference_frame)
+				if numpy.any(abstract_reference_frame):
+					abstract_reference_faces = sort_and_filter_faces(get_many_faces([ abstract_reference_frame ]))
+					abstract_reference_face = get_one_face(abstract_reference_faces, state_manager.get_item('reference_face_position'))
+					append_reference_face(processor_module.__name__, abstract_reference_face)
 
 
 def process_image(start_time : float) -> ErrorCode:
 	if analyse_image(state_manager.get_item('target_path')):
 		return 3
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# create temp
 	logger.debug(wording.get('creating_temp'), __name__)
 	create_temp_directory(state_manager.get_item('target_path'))
-	# copy image
+
 	process_manager.start()
 	temp_image_resolution = pack_resolution(restrict_image_resolution(state_manager.get_item('target_path'), unpack_resolution(state_manager.get_item('output_image_resolution'))))
 	logger.info(wording.get('copying_image').format(resolution = temp_image_resolution), __name__)
@@ -320,29 +390,28 @@ def process_image(start_time : float) -> ErrorCode:
 		logger.error(wording.get('copying_image_failed'), __name__)
 		process_manager.end()
 		return 1
-	# process image
-	temp_file_path = get_temp_file_path(state_manager.get_item('target_path'))
+
+	temp_image_path = get_temp_file_path(state_manager.get_item('target_path'))
 	for processor_module in get_processors_modules(state_manager.get_item('processors')):
 		logger.info(wording.get('processing'), processor_module.__name__)
-		processor_module.process_image(state_manager.get_item('source_paths'), temp_file_path, temp_file_path)
+		processor_module.process_image(state_manager.get_item('source_paths'), temp_image_path, temp_image_path)
 		processor_module.post_process()
 	if is_process_stopping():
 		process_manager.end()
 		return 4
-	# finalize image
+
 	logger.info(wording.get('finalizing_image').format(resolution = state_manager.get_item('output_image_resolution')), __name__)
 	if finalize_image(state_manager.get_item('target_path'), state_manager.get_item('output_path'), state_manager.get_item('output_image_resolution')):
 		logger.debug(wording.get('finalizing_image_succeed'), __name__)
 	else:
 		logger.warn(wording.get('finalizing_image_skipped'), __name__)
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# validate image
+
 	if is_image(state_manager.get_item('output_path')):
 		seconds = '{:.2f}'.format((time() - start_time) % 60)
 		logger.info(wording.get('processing_image_succeed').format(seconds = seconds), __name__)
-		conditional_log_statistics()
 	else:
 		logger.error(wording.get('processing_image_failed'), __name__)
 		process_manager.end()
@@ -352,20 +421,20 @@ def process_image(start_time : float) -> ErrorCode:
 
 
 def process_video(start_time : float) -> ErrorCode:
-	if analyse_video(state_manager.get_item('target_path'), state_manager.get_item('trim_frame_start'), state_manager.get_item('trim_frame_end')):
+	trim_frame_start, trim_frame_end = restrict_trim_frame(state_manager.get_item('target_path'), state_manager.get_item('trim_frame_start'), state_manager.get_item('trim_frame_end'))
+	if analyse_video(state_manager.get_item('target_path'), trim_frame_start, trim_frame_end):
 		return 3
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# create temp
 	logger.debug(wording.get('creating_temp'), __name__)
 	create_temp_directory(state_manager.get_item('target_path'))
-	# extract frames
+
 	process_manager.start()
 	temp_video_resolution = pack_resolution(restrict_video_resolution(state_manager.get_item('target_path'), unpack_resolution(state_manager.get_item('output_video_resolution'))))
 	temp_video_fps = restrict_video_fps(state_manager.get_item('target_path'), state_manager.get_item('output_video_fps'))
 	logger.info(wording.get('extracting_frames').format(resolution = temp_video_resolution, fps = temp_video_fps), __name__)
-	if extract_frames(state_manager.get_item('target_path'), temp_video_resolution, temp_video_fps):
+	if extract_frames(state_manager.get_item('target_path'), temp_video_resolution, temp_video_fps, trim_frame_start, trim_frame_end):
 		logger.debug(wording.get('extracting_frames_succeed'), __name__)
 	else:
 		if is_process_stopping():
@@ -374,8 +443,8 @@ def process_video(start_time : float) -> ErrorCode:
 		logger.error(wording.get('extracting_frames_failed'), __name__)
 		process_manager.end()
 		return 1
-	# process frames
-	temp_frame_paths = get_temp_frame_paths(state_manager.get_item('target_path'))
+
+	temp_frame_paths = resolve_temp_frame_paths(state_manager.get_item('target_path'))
 	if temp_frame_paths:
 		for processor_module in get_processors_modules(state_manager.get_item('processors')):
 			logger.info(wording.get('processing'), processor_module.__name__)
@@ -387,9 +456,9 @@ def process_video(start_time : float) -> ErrorCode:
 		logger.error(wording.get('temp_frames_not_found'), __name__)
 		process_manager.end()
 		return 1
-	# merge video
+
 	logger.info(wording.get('merging_video').format(resolution = state_manager.get_item('output_video_resolution'), fps = state_manager.get_item('output_video_fps')), __name__)
-	if merge_video(state_manager.get_item('target_path'), state_manager.get_item('output_video_resolution'), state_manager.get_item('output_video_fps')):
+	if merge_video(state_manager.get_item('target_path'), temp_video_fps, state_manager.get_item('output_video_resolution'), state_manager.get_item('output_video_fps'), trim_frame_start, trim_frame_end):
 		logger.debug(wording.get('merging_video_succeed'), __name__)
 	else:
 		if is_process_stopping():
@@ -398,38 +467,41 @@ def process_video(start_time : float) -> ErrorCode:
 		logger.error(wording.get('merging_video_failed'), __name__)
 		process_manager.end()
 		return 1
-	# handle audio
-	if state_manager.get_item('skip_audio'):
+
+	if state_manager.get_item('output_audio_volume') == 0:
 		logger.info(wording.get('skipping_audio'), __name__)
 		move_temp_file(state_manager.get_item('target_path'), state_manager.get_item('output_path'))
 	else:
 		source_audio_path = get_first(filter_audio_paths(state_manager.get_item('source_paths')))
 		if source_audio_path:
 			if replace_audio(state_manager.get_item('target_path'), source_audio_path, state_manager.get_item('output_path')):
+				video_manager.clear_video_pool()
 				logger.debug(wording.get('replacing_audio_succeed'), __name__)
 			else:
+				video_manager.clear_video_pool()
 				if is_process_stopping():
 					process_manager.end()
 					return 4
 				logger.warn(wording.get('replacing_audio_skipped'), __name__)
 				move_temp_file(state_manager.get_item('target_path'), state_manager.get_item('output_path'))
 		else:
-			if restore_audio(state_manager.get_item('target_path'), state_manager.get_item('output_path'), state_manager.get_item('output_video_fps')):
+			if restore_audio(state_manager.get_item('target_path'), state_manager.get_item('output_path'), trim_frame_start, trim_frame_end):
+				video_manager.clear_video_pool()
 				logger.debug(wording.get('restoring_audio_succeed'), __name__)
 			else:
+				video_manager.clear_video_pool()
 				if is_process_stopping():
 					process_manager.end()
 					return 4
 				logger.warn(wording.get('restoring_audio_skipped'), __name__)
 				move_temp_file(state_manager.get_item('target_path'), state_manager.get_item('output_path'))
-	# clear temp
+
 	logger.debug(wording.get('clearing_temp'), __name__)
 	clear_temp_directory(state_manager.get_item('target_path'))
-	# validate video
+
 	if is_video(state_manager.get_item('output_path')):
 		seconds = '{:.2f}'.format((time() - start_time))
 		logger.info(wording.get('processing_video_succeed').format(seconds = seconds), __name__)
-		conditional_log_statistics()
 	else:
 		logger.error(wording.get('processing_video_failed'), __name__)
 		process_manager.end()

facefusion/curl_builder.py

@@ -0,0 +1,27 @@
+import itertools
+import shutil
+
+from facefusion import metadata
+from facefusion.types import Commands
+
+
+def run(commands : Commands) -> Commands:
+	user_agent = metadata.get('name') + '/' + metadata.get('version')
+
+	return [ shutil.which('curl'), '--user-agent', user_agent, '--insecure', '--location', '--silent' ] + commands
+
+
+def chain(*commands : Commands) -> Commands:
+	return list(itertools.chain(*commands))
+
+
+def head(url : str) -> Commands:
+	return [ '-I', url ]
+
+
+def download(url : str, download_file_path : str) -> Commands:
+	return [ '--create-dirs', '--continue-at', '-', '--output', download_file_path, url ]
+
+
+def set_timeout(timeout : int) -> Commands:
+	return [ '--connect-timeout', str(timeout) ]

facefusion/download.py

@@ -1,22 +1,21 @@
 import os
-import shutil
-import ssl
 import subprocess
-import urllib.request
 from functools import lru_cache
-from typing import List, Tuple
+from typing import List, Optional, Tuple
 from urllib.parse import urlparse
 
 from tqdm import tqdm
 
-from facefusion import logger, process_manager, state_manager, wording
-from facefusion.common_helper import is_macos
-from facefusion.filesystem import get_file_size, is_file, remove_file
+import facefusion.choices
+from facefusion import curl_builder, logger, process_manager, state_manager, wording
+from facefusion.filesystem import get_file_name, get_file_size, is_file, remove_file
 from facefusion.hash_helper import validate_hash
-from facefusion.typing import DownloadSet
+from facefusion.types import Commands, DownloadProvider, DownloadSet
 
-if is_macos():
-	ssl._create_default_https_context = ssl._create_unverified_context
+
+def open_curl(commands : Commands) -> subprocess.Popen[bytes]:
+	commands = curl_builder.run(commands)
+	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)
 
 
 def conditional_download(download_directory_path : str, urls : List[str]) -> None:
@@ -24,14 +23,18 @@ def conditional_download(download_directory_path : str, urls : List[str]) -> Non
 		download_file_name = os.path.basename(urlparse(url).path)
 		download_file_path = os.path.join(download_directory_path, download_file_name)
 		initial_size = get_file_size(download_file_path)
-		download_size = get_download_size(url)
+		download_size = get_static_download_size(url)
 
 		if initial_size < download_size:
 			with tqdm(total = download_size, initial = initial_size, desc = wording.get('downloading'), unit = 'B', unit_scale = True, unit_divisor = 1024, ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
-				subprocess.Popen([ shutil.which('curl'), '--create-dirs', '--silent', '--insecure', '--location', '--continue-at', '-', '--output', download_file_path, url ])
+				commands = curl_builder.chain(
+					curl_builder.download(url, download_file_path),
+					curl_builder.set_timeout(10)
+				)
+				open_curl(commands)
 				current_size = initial_size
+				progress.set_postfix(download_providers = state_manager.get_item('download_providers'), file_name = download_file_name)
 
-				progress.set_postfix(file = download_file_name)
 				while current_size < download_size:
 					if is_file(download_file_path):
 						current_size = get_file_size(download_file_path)
@@ -39,39 +42,54 @@ def conditional_download(download_directory_path : str, urls : List[str]) -> Non
 
 
 @lru_cache(maxsize = None)
-def get_download_size(url : str) -> int:
-	try:
-		response = urllib.request.urlopen(url, timeout = 10)
-		content_length = response.headers.get('Content-Length')
-		return int(content_length)
-	except (OSError, TypeError, ValueError):
-		return 0
+def get_static_download_size(url : str) -> int:
+	commands = curl_builder.chain(
+		curl_builder.head(url),
+		curl_builder.set_timeout(5)
+	)
+	process = open_curl(commands)
+	lines = reversed(process.stdout.readlines())
+
+	for line in lines:
+		__line__ = line.decode().lower()
+		if 'content-length:' in __line__:
+			_, content_length = __line__.split('content-length:')
+			return int(content_length)
+
+	return 0
 
 
-def is_download_done(url : str, file_path : str) -> bool:
-	if is_file(file_path):
-		return get_download_size(url) == get_file_size(file_path)
-	return False
+@lru_cache(maxsize = None)
+def ping_static_url(url : str) -> bool:
+	commands = curl_builder.chain(
+		curl_builder.head(url),
+		curl_builder.set_timeout(5)
+	)
+	process = open_curl(commands)
+	process.communicate()
+	return process.returncode == 0
 
 
-def conditional_download_hashes(download_directory_path : str, hashes : DownloadSet) -> bool:
-	hash_paths = [ hashes.get(hash_key).get('path') for hash_key in hashes.keys() ]
+def conditional_download_hashes(hash_set : DownloadSet) -> bool:
+	hash_paths = [ hash_set.get(hash_key).get('path') for hash_key in hash_set.keys() ]
 
 	process_manager.check()
-	if not state_manager.get_item('skip_download'):
-		_, invalid_hash_paths = validate_hash_paths(hash_paths)
-		if invalid_hash_paths:
-			for index in hashes:
-				if hashes.get(index).get('path') in invalid_hash_paths:
-					invalid_hash_url = hashes.get(index).get('url')
+	_, invalid_hash_paths = validate_hash_paths(hash_paths)
+	if invalid_hash_paths:
+		for index in hash_set:
+			if hash_set.get(index).get('path') in invalid_hash_paths:
+				invalid_hash_url = hash_set.get(index).get('url')
+				if invalid_hash_url:
+					download_directory_path = os.path.dirname(hash_set.get(index).get('path'))
 					conditional_download(download_directory_path, [ invalid_hash_url ])
 
 	valid_hash_paths, invalid_hash_paths = validate_hash_paths(hash_paths)
+
 	for valid_hash_path in valid_hash_paths:
-		valid_hash_file_name, _ = os.path.splitext(os.path.basename(valid_hash_path))
+		valid_hash_file_name = get_file_name(valid_hash_path)
 		logger.debug(wording.get('validating_hash_succeed').format(hash_file_name = valid_hash_file_name), __name__)
 	for invalid_hash_path in invalid_hash_paths:
-		invalid_hash_file_name, _ = os.path.splitext(os.path.basename(invalid_hash_path))
+		invalid_hash_file_name = get_file_name(invalid_hash_path)
 		logger.error(wording.get('validating_hash_failed').format(hash_file_name = invalid_hash_file_name), __name__)
 
 	if not invalid_hash_paths:
@@ -79,24 +97,26 @@ def conditional_download_hashes(download_directory_path : str, hashes : Download
 	return not invalid_hash_paths
 
 
-def conditional_download_sources(download_directory_path : str, sources : DownloadSet) -> bool:
-	source_paths = [ sources.get(source_key).get('path') for source_key in sources.keys() ]
+def conditional_download_sources(source_set : DownloadSet) -> bool:
+	source_paths = [ source_set.get(source_key).get('path') for source_key in source_set.keys() ]
 
 	process_manager.check()
-	if not state_manager.get_item('skip_download'):
-		_, invalid_source_paths = validate_source_paths(source_paths)
-		if invalid_source_paths:
-			for index in sources:
-				if sources.get(index).get('path') in invalid_source_paths:
-					invalid_source_url = sources.get(index).get('url')
+	_, invalid_source_paths = validate_source_paths(source_paths)
+	if invalid_source_paths:
+		for index in source_set:
+			if source_set.get(index).get('path') in invalid_source_paths:
+				invalid_source_url = source_set.get(index).get('url')
+				if invalid_source_url:
+					download_directory_path = os.path.dirname(source_set.get(index).get('path'))
 					conditional_download(download_directory_path, [ invalid_source_url ])
 
 	valid_source_paths, invalid_source_paths = validate_source_paths(source_paths)
+
 	for valid_source_path in valid_source_paths:
-		valid_source_file_name, _ = os.path.splitext(os.path.basename(valid_source_path))
+		valid_source_file_name = get_file_name(valid_source_path)
 		logger.debug(wording.get('validating_source_succeed').format(source_file_name = valid_source_file_name), __name__)
 	for invalid_source_path in invalid_source_paths:
-		invalid_source_file_name, _ = os.path.splitext(os.path.basename(invalid_source_path))
+		invalid_source_file_name = get_file_name(invalid_source_path)
 		logger.error(wording.get('validating_source_failed').format(source_file_name = invalid_source_file_name), __name__)
 
 		if remove_file(invalid_source_path):
@@ -116,6 +136,7 @@ def validate_hash_paths(hash_paths : List[str]) -> Tuple[List[str], List[str]]:
 			valid_hash_paths.append(hash_path)
 		else:
 			invalid_hash_paths.append(hash_path)
+
 	return valid_hash_paths, invalid_hash_paths
 
 
@@ -128,4 +149,26 @@ def validate_source_paths(source_paths : List[str]) -> Tuple[List[str], List[str
 			valid_source_paths.append(source_path)
 		else:
 			invalid_source_paths.append(source_path)
+
 	return valid_source_paths, invalid_source_paths
+
+
+def resolve_download_url(base_name : str, file_name : str) -> Optional[str]:
+	download_providers = state_manager.get_item('download_providers')
+
+	for download_provider in download_providers:
+		download_url = resolve_download_url_by_provider(download_provider, base_name, file_name)
+		if download_url:
+			return download_url
+
+	return None
+
+
+def resolve_download_url_by_provider(download_provider : DownloadProvider, base_name : str, file_name : str) -> Optional[str]:
+	download_provider_value = facefusion.choices.download_provider_set.get(download_provider)
+
+	for download_provider_url in download_provider_value.get('urls'):
+		if ping_static_url(download_provider_url):
+			return download_provider_url + download_provider_value.get('path').format(base_name = base_name, file_name = file_name)
+
+	return None

facefusion/execution.py

@@ -1,46 +1,45 @@
+import shutil
 import subprocess
 import xml.etree.ElementTree as ElementTree
 from functools import lru_cache
-from typing import Any, List
+from typing import List, Optional
 
 from onnxruntime import get_available_providers, set_default_logger_severity
 
-from facefusion.choices import execution_provider_set
-from facefusion.typing import ExecutionDevice, ExecutionProviderKey, ExecutionProviderSet, ValueAndUnit
+import facefusion.choices
+from facefusion.types import ExecutionDevice, ExecutionProvider, InferenceSessionProvider, ValueAndUnit
 
 set_default_logger_severity(3)
 
 
-def get_execution_provider_choices() -> List[ExecutionProviderKey]:
-	return list(get_available_execution_provider_set().keys())
+def has_execution_provider(execution_provider : ExecutionProvider) -> bool:
+	return execution_provider in get_available_execution_providers()
 
 
-def has_execution_provider(execution_provider_key : ExecutionProviderKey) -> bool:
-	return execution_provider_key in get_execution_provider_choices()
+def get_available_execution_providers() -> List[ExecutionProvider]:
+	inference_session_providers = get_available_providers()
+	available_execution_providers : List[ExecutionProvider] = []
+
+	for execution_provider, execution_provider_value in facefusion.choices.execution_provider_set.items():
+		if execution_provider_value in inference_session_providers:
+			index = facefusion.choices.execution_providers.index(execution_provider)
+			available_execution_providers.insert(index, execution_provider)
+
+	return available_execution_providers
 
 
-def get_available_execution_provider_set() -> ExecutionProviderSet:
-	available_execution_providers = get_available_providers()
-	available_execution_provider_set : ExecutionProviderSet = {}
+def create_inference_session_providers(execution_device_id : str, execution_providers : List[ExecutionProvider]) -> List[InferenceSessionProvider]:
+	inference_session_providers : List[InferenceSessionProvider] = []
 
-	for execution_provider_key, execution_provider_value in execution_provider_set.items():
-		if execution_provider_value in available_execution_providers:
-			available_execution_provider_set[execution_provider_key] = execution_provider_value
-	return available_execution_provider_set
-
-
-def create_execution_providers(execution_device_id : str, execution_provider_keys : List[ExecutionProviderKey]) -> List[Any]:
-	execution_providers : List[Any] = []
-
-	for execution_provider_key in execution_provider_keys:
-		if execution_provider_key == 'cuda':
-			execution_providers.append((execution_provider_set.get(execution_provider_key),
+	for execution_provider in execution_providers:
+		if execution_provider == 'cuda':
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id,
-				'cudnn_conv_algo_search': 'EXHAUSTIVE' if use_exhaustive() else 'DEFAULT'
+				'cudnn_conv_algo_search': resolve_cudnn_conv_algo_search()
 			}))
-		if execution_provider_key == 'tensorrt':
-			execution_providers.append((execution_provider_set.get(execution_provider_key),
+		if execution_provider == 'tensorrt':
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id,
 				'trt_engine_cache_enable': True,
@@ -49,35 +48,51 @@ def create_execution_providers(execution_device_id : str, execution_provider_key
 				'trt_timing_cache_path': '.caches',
 				'trt_builder_optimization_level': 5
 			}))
-		if execution_provider_key == 'openvino':
-			execution_providers.append((execution_provider_set.get(execution_provider_key),
-			{
-				'device_type': 'GPU.' + execution_device_id,
-				'precision': 'FP32'
-			}))
-		if execution_provider_key in [ 'directml', 'rocm' ]:
-			execution_providers.append((execution_provider_set.get(execution_provider_key),
+		if execution_provider in [ 'directml', 'rocm' ]:
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
 			{
 				'device_id': execution_device_id
 			}))
-		if execution_provider_key == 'coreml':
-			execution_providers.append(execution_provider_set.get(execution_provider_key))
+		if execution_provider == 'openvino':
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			{
+				'device_type': resolve_openvino_device_type(execution_device_id),
+				'precision': 'FP32'
+			}))
+		if execution_provider == 'coreml':
+			inference_session_providers.append((facefusion.choices.execution_provider_set.get(execution_provider),
+			{
+				'SpecializationStrategy': 'FastPrediction',
+				'ModelCacheDirectory': '.caches'
+			}))
 
-	if 'cpu' in execution_provider_keys:
-		execution_providers.append(execution_provider_set.get('cpu'))
+	if 'cpu' in execution_providers:
+		inference_session_providers.append(facefusion.choices.execution_provider_set.get('cpu'))
 
-	return execution_providers
+	return inference_session_providers
 
 
-def use_exhaustive() -> bool:
+def resolve_cudnn_conv_algo_search() -> str:
 	execution_devices = detect_static_execution_devices()
 	product_names = ('GeForce GTX 1630', 'GeForce GTX 1650', 'GeForce GTX 1660')
 
-	return any(execution_device.get('product').get('name').startswith(product_names) for execution_device in execution_devices)
+	for execution_device in execution_devices:
+		if execution_device.get('product').get('name').startswith(product_names):
+			return 'DEFAULT'
+
+	return 'EXHAUSTIVE'
+
+
+def resolve_openvino_device_type(execution_device_id : str) -> str:
+	if execution_device_id == '0':
+		return 'GPU'
+	if execution_device_id == '∞':
+		return 'MULTI:GPU'
+	return 'GPU.' + execution_device_id
 
 
 def run_nvidia_smi() -> subprocess.Popen[bytes]:
-	commands = [ 'nvidia-smi', '--query', '--xml-format' ]
+	commands = [ shutil.which('nvidia-smi'), '--query', '--xml-format' ]
 	return subprocess.Popen(commands, stdout = subprocess.PIPE)
 
 
@@ -98,37 +113,44 @@ def detect_execution_devices() -> List[ExecutionDevice]:
 	for gpu_element in root_element.findall('gpu'):
 		execution_devices.append(
 		{
-			'driver_version': root_element.find('driver_version').text,
+			'driver_version': root_element.findtext('driver_version'),
 			'framework':
 			{
 				'name': 'CUDA',
-				'version': root_element.find('cuda_version').text
+				'version': root_element.findtext('cuda_version')
 			},
 			'product':
 			{
 				'vendor': 'NVIDIA',
-				'name': gpu_element.find('product_name').text.replace('NVIDIA ', '')
+				'name': gpu_element.findtext('product_name').replace('NVIDIA', '').strip()
 			},
 			'video_memory':
 			{
-				'total': create_value_and_unit(gpu_element.find('fb_memory_usage/total').text),
-				'free': create_value_and_unit(gpu_element.find('fb_memory_usage/free').text)
+				'total': create_value_and_unit(gpu_element.findtext('fb_memory_usage/total')),
+				'free': create_value_and_unit(gpu_element.findtext('fb_memory_usage/free'))
+			},
+			'temperature':
+			{
+				'gpu': create_value_and_unit(gpu_element.findtext('temperature/gpu_temp')),
+				'memory': create_value_and_unit(gpu_element.findtext('temperature/memory_temp'))
 			},
 			'utilization':
 			{
-				'gpu': create_value_and_unit(gpu_element.find('utilization/gpu_util').text),
-				'memory': create_value_and_unit(gpu_element.find('utilization/memory_util').text)
+				'gpu': create_value_and_unit(gpu_element.findtext('utilization/gpu_util')),
+				'memory': create_value_and_unit(gpu_element.findtext('utilization/memory_util'))
 			}
 		})
+
 	return execution_devices
 
 
-def create_value_and_unit(text : str) -> ValueAndUnit:
-	value, unit = text.split()
-	value_and_unit : ValueAndUnit =\
-	{
-		'value': int(value),
-		'unit': str(unit)
-	}
+def create_value_and_unit(text : str) -> Optional[ValueAndUnit]:
+	if ' ' in text:
+		value, unit = text.split()
 
-	return value_and_unit
+		return\
+		{
+			'value': int(value),
+			'unit': str(unit)
+		}
+	return None

facefusion/exit_helper.py

@@ -1,18 +1,20 @@
+import signal
 import sys
 from time import sleep
+from types import FrameType
 
 from facefusion import process_manager, state_manager
 from facefusion.temp_helper import clear_temp_directory
-from facefusion.typing import ErrorCode
+from facefusion.types import ErrorCode
 
 
 def hard_exit(error_code : ErrorCode) -> None:
+	signal.signal(signal.SIGINT, signal.SIG_IGN)
 	sys.exit(error_code)
 
 
-def conditional_exit(error_code : ErrorCode) -> None:
-	if state_manager.get_item('command') == 'headless-run':
-		hard_exit(error_code)
+def signal_exit(signum : int, frame : FrameType) -> None:
+	graceful_exit(0)
 
 
 def graceful_exit(error_code : ErrorCode) -> None:

facefusion/face_analyser.py

@@ -7,10 +7,10 @@ from facefusion.common_helper import get_first
 from facefusion.face_classifier import classify_face
 from facefusion.face_detector import detect_faces, detect_rotated_faces
 from facefusion.face_helper import apply_nms, convert_to_face_landmark_5, estimate_face_angle, get_nms_threshold
-from facefusion.face_landmarker import detect_face_landmarks, estimate_face_landmark_68_5
+from facefusion.face_landmarker import detect_face_landmark, estimate_face_landmark_68_5
 from facefusion.face_recognizer import calc_embedding
 from facefusion.face_store import get_static_faces, set_static_faces
-from facefusion.typing import BoundingBox, Face, FaceLandmark5, FaceLandmarkSet, FaceScoreSet, Score, VisionFrame
+from facefusion.types import BoundingBox, Face, FaceLandmark5, FaceLandmarkSet, FaceScoreSet, Score, VisionFrame
 
 
 def create_faces(vision_frame : VisionFrame, bounding_boxes : List[BoundingBox], face_scores : List[Score], face_landmarks_5 : List[FaceLandmark5]) -> List[Face]:
@@ -29,7 +29,7 @@ def create_faces(vision_frame : VisionFrame, bounding_boxes : List[BoundingBox],
 		face_angle = estimate_face_angle(face_landmark_68_5)
 
 		if state_manager.get_item('face_landmarker_score') > 0:
-			face_landmark_68, face_landmark_score_68 = detect_face_landmarks(vision_frame, bounding_box, face_angle)
+			face_landmark_68, face_landmark_score_68 = detect_face_landmark(vision_frame, bounding_box, face_angle)
 		if face_landmark_score_68 > state_manager.get_item('face_landmarker_score'):
 			face_landmark_5_68 = convert_to_face_landmark_5(face_landmark_68)
 

facefusion/face_classifier.py

@@ -1,61 +1,67 @@
+from functools import lru_cache
 from typing import List, Tuple
 
 import numpy
 
 from facefusion import inference_manager
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_helper import warp_face_by_face_landmark_5
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import Age, FaceLandmark5, Gender, InferencePool, ModelOptions, ModelSet, Race, VisionFrame
+from facefusion.types import Age, DownloadScope, FaceLandmark5, Gender, InferencePool, ModelOptions, ModelSet, Race, VisionFrame
 
-MODEL_SET : ModelSet =\
-{
-	'fairface':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'fairface':
 		{
-			'face_classifier':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/fairface.hash',
-				'path': resolve_relative_path('../.assets/models/fairface.hash')
-			}
-		},
-		'sources':
-		{
-			'face_classifier':
+				'face_classifier':
+				{
+					'url': resolve_download_url('models-3.0.0', 'fairface.hash'),
+					'path': resolve_relative_path('../.assets/models/fairface.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/fairface.onnx',
-				'path': resolve_relative_path('../.assets/models/fairface.onnx')
-			}
-		},
-		'template': 'arcface_112_v2',
-		'size': (224, 224),
-		'mean': [ 0.485, 0.456, 0.406 ],
-		'standard_deviation': [ 0.229, 0.224, 0.225 ]
+				'face_classifier':
+				{
+					'url': resolve_download_url('models-3.0.0', 'fairface.onnx'),
+					'path': resolve_relative_path('../.assets/models/fairface.onnx')
+				}
+			},
+			'template': 'arcface_112_v2',
+			'size': (224, 224),
+			'mean': [ 0.485, 0.456, 0.406 ],
+			'standard_deviation': [ 0.229, 0.224, 0.225 ]
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ 'fairface' ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ 'fairface' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	return MODEL_SET.get('fairface')
+	return create_static_model_set('full').get('fairface')
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def classify_face(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5) -> Tuple[Gender, Age, Race]:
@@ -64,7 +70,7 @@ def classify_face(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmar
 	model_mean = get_model_options().get('mean')
 	model_standard_deviation = get_model_options().get('standard_deviation')
 	crop_vision_frame, _ = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_template, model_size)
-	crop_vision_frame = crop_vision_frame.astype(numpy.float32)[:, :, ::-1] / 255
+	crop_vision_frame = crop_vision_frame.astype(numpy.float32)[:, :, ::-1] / 255.0
 	crop_vision_frame -= model_mean
 	crop_vision_frame /= model_standard_deviation
 	crop_vision_frame = crop_vision_frame.transpose(2, 0, 1)

facefusion/face_detector.py

@@ -1,110 +1,111 @@
-from typing import List, Tuple
+from functools import lru_cache
+from typing import List, Sequence, Tuple
 
 import cv2
 import numpy
 
 from facefusion import inference_manager, state_manager
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_helper import create_rotated_matrix_and_size, create_static_anchors, distance_to_bounding_box, distance_to_face_landmark_5, normalize_bounding_box, transform_bounding_box, transform_points
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import Angle, BoundingBox, Detection, DownloadSet, FaceLandmark5, InferencePool, ModelSet, Score, VisionFrame
-from facefusion.vision import resize_frame_resolution, unpack_resolution
+from facefusion.types import Angle, BoundingBox, Detection, DownloadScope, DownloadSet, FaceLandmark5, InferencePool, ModelSet, Score, VisionFrame
+from facefusion.vision import restrict_frame, unpack_resolution
 
-MODEL_SET : ModelSet =\
-{
-	'retinaface':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'retinaface':
 		{
-			'retinaface':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/retinaface_10g.hash',
-				'path': resolve_relative_path('../.assets/models/retinaface_10g.hash')
+				'retinaface':
+				{
+					'url': resolve_download_url('models-3.0.0', 'retinaface_10g.hash'),
+					'path': resolve_relative_path('../.assets/models/retinaface_10g.hash')
+				}
+			},
+			'sources':
+			{
+				'retinaface':
+				{
+					'url': resolve_download_url('models-3.0.0', 'retinaface_10g.onnx'),
+					'path': resolve_relative_path('../.assets/models/retinaface_10g.onnx')
+				}
 			}
 		},
-		'sources':
+		'scrfd':
 		{
-			'retinaface':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/retinaface_10g.onnx',
-				'path': resolve_relative_path('../.assets/models/retinaface_10g.onnx')
-			}
-		}
-	},
-	'scrfd':
-	{
-		'hashes':
-		{
-			'scrfd':
+				'scrfd':
+				{
+					'url': resolve_download_url('models-3.0.0', 'scrfd_2.5g.hash'),
+					'path': resolve_relative_path('../.assets/models/scrfd_2.5g.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/scrfd_2.5g.hash',
-				'path': resolve_relative_path('../.assets/models/scrfd_2.5g.hash')
+				'scrfd':
+				{
+					'url': resolve_download_url('models-3.0.0', 'scrfd_2.5g.onnx'),
+					'path': resolve_relative_path('../.assets/models/scrfd_2.5g.onnx')
+				}
 			}
 		},
-		'sources':
+		'yolo_face':
 		{
-			'scrfd':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/scrfd_2.5g.onnx',
-				'path': resolve_relative_path('../.assets/models/scrfd_2.5g.onnx')
-			}
-		}
-	},
-	'yoloface':
-	{
-		'hashes':
-		{
-			'yoloface':
+				'yolo_face':
+				{
+					'url': resolve_download_url('models-3.0.0', 'yoloface_8n.hash'),
+					'path': resolve_relative_path('../.assets/models/yoloface_8n.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/yoloface_8n.hash',
-				'path': resolve_relative_path('../.assets/models/yoloface_8n.hash')
-			}
-		},
-		'sources':
-		{
-			'yoloface':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/yoloface_8n.onnx',
-				'path': resolve_relative_path('../.assets/models/yoloface_8n.onnx')
+				'yolo_face':
+				{
+					'url': resolve_download_url('models-3.0.0', 'yoloface_8n.onnx'),
+					'path': resolve_relative_path('../.assets/models/yoloface_8n.onnx')
+				}
 			}
 		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	_, model_sources = collect_model_downloads()
-	model_context = __name__ + '.' + state_manager.get_item('face_detector_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('face_detector_model') ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('face_detector_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ state_manager.get_item('face_detector_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
-	model_hashes = {}
-	model_sources = {}
+	model_set = create_static_model_set('full')
+	model_hash_set = {}
+	model_source_set = {}
 
-	if state_manager.get_item('face_detector_model') in [ 'many', 'retinaface' ]:
-		model_hashes['retinaface'] = MODEL_SET.get('retinaface').get('hashes').get('retinaface')
-		model_sources['retinaface'] = MODEL_SET.get('retinaface').get('sources').get('retinaface')
-	if state_manager.get_item('face_detector_model') in [ 'many', 'scrfd' ]:
-		model_hashes['scrfd'] = MODEL_SET.get('scrfd').get('hashes').get('scrfd')
-		model_sources['scrfd'] = MODEL_SET.get('scrfd').get('sources').get('scrfd')
-	if state_manager.get_item('face_detector_model') in [ 'many', 'yoloface' ]:
-		model_hashes['yoloface'] = MODEL_SET.get('yoloface').get('hashes').get('yoloface')
-		model_sources['yoloface'] = MODEL_SET.get('yoloface').get('sources').get('yoloface')
-	return model_hashes, model_sources
+	for face_detector_model in [ 'retinaface', 'scrfd', 'yolo_face' ]:
+		if state_manager.get_item('face_detector_model') in [ 'many', face_detector_model ]:
+			model_hash_set[face_detector_model] = model_set.get(face_detector_model).get('hashes').get(face_detector_model)
+			model_source_set[face_detector_model] = model_set.get(face_detector_model).get('sources').get(face_detector_model)
+
+	return model_hash_set, model_source_set
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes, model_sources = collect_model_downloads()
+	model_hash_set, model_source_set = collect_model_downloads()
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def detect_faces(vision_frame : VisionFrame) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
@@ -124,8 +125,8 @@ def detect_faces(vision_frame : VisionFrame) -> Tuple[List[BoundingBox], List[Sc
 		all_face_scores.extend(face_scores)
 		all_face_landmarks_5.extend(face_landmarks_5)
 
-	if state_manager.get_item('face_detector_model') in [ 'many', 'yoloface' ]:
-		bounding_boxes, face_scores, face_landmarks_5 = detect_with_yoloface(vision_frame, state_manager.get_item('face_detector_size'))
+	if state_manager.get_item('face_detector_model') in [ 'many', 'yolo_face' ]:
+		bounding_boxes, face_scores, face_landmarks_5 = detect_with_yolo_face(vision_frame, state_manager.get_item('face_detector_size'))
 		all_bounding_boxes.extend(bounding_boxes)
 		all_face_scores.extend(face_scores)
 		all_face_landmarks_5.extend(face_landmarks_5)
@@ -151,37 +152,39 @@ def detect_with_retinaface(vision_frame : VisionFrame, face_detector_size : str)
 	feature_strides = [ 8, 16, 32 ]
 	feature_map_channel = 3
 	anchor_total = 2
+	face_detector_score = state_manager.get_item('face_detector_score')
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
-	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	temp_vision_frame = restrict_frame(vision_frame, (face_detector_width, face_detector_height))
 	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
 	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
 	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	detect_vision_frame = normalize_detect_frame(detect_vision_frame, [ -1, 1 ])
 	detection = forward_with_retinaface(detect_vision_frame)
 
 	for index, feature_stride in enumerate(feature_strides):
-		keep_indices = numpy.where(detection[index] >= state_manager.get_item('face_detector_score'))[0]
+		keep_indices = numpy.where(detection[index] >= face_detector_score)[0]
 
 		if numpy.any(keep_indices):
 			stride_height = face_detector_height // feature_stride
 			stride_width = face_detector_width // feature_stride
 			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
-			bounding_box_raw = detection[index + feature_map_channel] * feature_stride
-			face_landmark_5_raw = detection[index + feature_map_channel * 2] * feature_stride
+			bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride
+			face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride
 
-			for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]:
+			for bounding_box_raw in distance_to_bounding_box(anchors, bounding_boxes_raw)[keep_indices]:
 				bounding_boxes.append(numpy.array(
 				[
-					bounding_box[0] * ratio_width,
-					bounding_box[1] * ratio_height,
-					bounding_box[2] * ratio_width,
-					bounding_box[3] * ratio_height,
+					bounding_box_raw[0] * ratio_width,
+					bounding_box_raw[1] * ratio_height,
+					bounding_box_raw[2] * ratio_width,
+					bounding_box_raw[3] * ratio_height
 				]))
 
-			for score in detection[index][keep_indices]:
-				face_scores.append(score[0])
+			for face_score_raw in detection[index][keep_indices]:
+				face_scores.append(face_score_raw[0])
 
-			for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]:
-				face_landmarks_5.append(face_landmark_5 * [ ratio_width, ratio_height ])
+			for face_landmark_raw_5 in distance_to_face_landmark_5(anchors, face_landmarks_5_raw)[keep_indices]:
+				face_landmarks_5.append(face_landmark_raw_5 * [ ratio_width, ratio_height ])
 
 	return bounding_boxes, face_scores, face_landmarks_5
 
@@ -193,73 +196,77 @@ def detect_with_scrfd(vision_frame : VisionFrame, face_detector_size : str) -> T
 	feature_strides = [ 8, 16, 32 ]
 	feature_map_channel = 3
 	anchor_total = 2
+	face_detector_score = state_manager.get_item('face_detector_score')
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
-	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	temp_vision_frame = restrict_frame(vision_frame, (face_detector_width, face_detector_height))
 	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
 	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
 	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
+	detect_vision_frame = normalize_detect_frame(detect_vision_frame, [ -1, 1 ])
 	detection = forward_with_scrfd(detect_vision_frame)
 
 	for index, feature_stride in enumerate(feature_strides):
-		keep_indices = numpy.where(detection[index] >= state_manager.get_item('face_detector_score'))[0]
+		keep_indices = numpy.where(detection[index] >= face_detector_score)[0]
 
 		if numpy.any(keep_indices):
 			stride_height = face_detector_height // feature_stride
 			stride_width = face_detector_width // feature_stride
 			anchors = create_static_anchors(feature_stride, anchor_total, stride_height, stride_width)
-			bounding_box_raw = detection[index + feature_map_channel] * feature_stride
-			face_landmark_5_raw = detection[index + feature_map_channel * 2] * feature_stride
+			bounding_boxes_raw = detection[index + feature_map_channel] * feature_stride
+			face_landmarks_5_raw = detection[index + feature_map_channel * 2] * feature_stride
 
-			for bounding_box in distance_to_bounding_box(anchors, bounding_box_raw)[keep_indices]:
+			for bounding_box_raw in distance_to_bounding_box(anchors, bounding_boxes_raw)[keep_indices]:
 				bounding_boxes.append(numpy.array(
 				[
-					bounding_box[0] * ratio_width,
-					bounding_box[1] * ratio_height,
-					bounding_box[2] * ratio_width,
-					bounding_box[3] * ratio_height,
+					bounding_box_raw[0] * ratio_width,
+					bounding_box_raw[1] * ratio_height,
+					bounding_box_raw[2] * ratio_width,
+					bounding_box_raw[3] * ratio_height
 				]))
 
-			for score in detection[index][keep_indices]:
-				face_scores.append(score[0])
+			for face_score_raw in detection[index][keep_indices]:
+				face_scores.append(face_score_raw[0])
 
-			for face_landmark_5 in distance_to_face_landmark_5(anchors, face_landmark_5_raw)[keep_indices]:
-				face_landmarks_5.append(face_landmark_5 * [ ratio_width, ratio_height ])
+			for face_landmark_raw_5 in distance_to_face_landmark_5(anchors, face_landmarks_5_raw)[keep_indices]:
+				face_landmarks_5.append(face_landmark_raw_5 * [ ratio_width, ratio_height ])
 
 	return bounding_boxes, face_scores, face_landmarks_5
 
 
-def detect_with_yoloface(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
+def detect_with_yolo_face(vision_frame : VisionFrame, face_detector_size : str) -> Tuple[List[BoundingBox], List[Score], List[FaceLandmark5]]:
 	bounding_boxes = []
 	face_scores = []
 	face_landmarks_5 = []
+	face_detector_score = state_manager.get_item('face_detector_score')
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
-	temp_vision_frame = resize_frame_resolution(vision_frame, (face_detector_width, face_detector_height))
+	temp_vision_frame = restrict_frame(vision_frame, (face_detector_width, face_detector_height))
 	ratio_height = vision_frame.shape[0] / temp_vision_frame.shape[0]
 	ratio_width = vision_frame.shape[1] / temp_vision_frame.shape[1]
 	detect_vision_frame = prepare_detect_frame(temp_vision_frame, face_detector_size)
-	detection = forward_with_yoloface(detect_vision_frame)
+	detect_vision_frame = normalize_detect_frame(detect_vision_frame, [ 0, 1 ])
+	detection = forward_with_yolo_face(detect_vision_frame)
 	detection = numpy.squeeze(detection).T
-	bounding_box_raw, score_raw, face_landmark_5_raw = numpy.split(detection, [ 4, 5 ], axis = 1)
-	keep_indices = numpy.where(score_raw > state_manager.get_item('face_detector_score'))[0]
+	bounding_boxes_raw, face_scores_raw, face_landmarks_5_raw = numpy.split(detection, [ 4, 5 ], axis = 1)
+	keep_indices = numpy.where(face_scores_raw > face_detector_score)[0]
 
 	if numpy.any(keep_indices):
-		bounding_box_raw, face_landmark_5_raw, score_raw = bounding_box_raw[keep_indices], face_landmark_5_raw[keep_indices], score_raw[keep_indices]
+		bounding_boxes_raw, face_scores_raw, face_landmarks_5_raw = bounding_boxes_raw[keep_indices], face_scores_raw[keep_indices], face_landmarks_5_raw[keep_indices]
 
-		for bounding_box in bounding_box_raw:
+		for bounding_box_raw in bounding_boxes_raw:
 			bounding_boxes.append(numpy.array(
 			[
-				(bounding_box[0] - bounding_box[2] / 2) * ratio_width,
-				(bounding_box[1] - bounding_box[3] / 2) * ratio_height,
-				(bounding_box[0] + bounding_box[2] / 2) * ratio_width,
-				(bounding_box[1] + bounding_box[3] / 2) * ratio_height,
+				(bounding_box_raw[0] - bounding_box_raw[2] / 2) * ratio_width,
+				(bounding_box_raw[1] - bounding_box_raw[3] / 2) * ratio_height,
+				(bounding_box_raw[0] + bounding_box_raw[2] / 2) * ratio_width,
+				(bounding_box_raw[1] + bounding_box_raw[3] / 2) * ratio_height
 			]))
 
-		face_scores = score_raw.ravel().tolist()
-		face_landmark_5_raw[:, 0::3] = (face_landmark_5_raw[:, 0::3]) * ratio_width
-		face_landmark_5_raw[:, 1::3] = (face_landmark_5_raw[:, 1::3]) * ratio_height
+		face_scores = face_scores_raw.ravel().tolist()
+		face_landmarks_5_raw[:, 0::3] = (face_landmarks_5_raw[:, 0::3]) * ratio_width
+		face_landmarks_5_raw[:, 1::3] = (face_landmarks_5_raw[:, 1::3]) * ratio_height
 
-		for face_landmark_5 in face_landmark_5_raw:
-			face_landmarks_5.append(numpy.array(face_landmark_5.reshape(-1, 3)[:, :2]))
+		for face_landmark_raw_5 in face_landmarks_5_raw:
+			face_landmarks_5.append(numpy.array(face_landmark_raw_5.reshape(-1, 3)[:, :2]))
 
 	return bounding_boxes, face_scores, face_landmarks_5
 
@@ -288,8 +295,8 @@ def forward_with_scrfd(detect_vision_frame : VisionFrame) -> Detection:
 	return detection
 
 
-def forward_with_yoloface(detect_vision_frame : VisionFrame) -> Detection:
-	face_detector = get_inference_pool().get('yoloface')
+def forward_with_yolo_face(detect_vision_frame : VisionFrame) -> Detection:
+	face_detector = get_inference_pool().get('yolo_face')
 
 	with thread_semaphore():
 		detection = face_detector.run(None,
@@ -304,6 +311,13 @@ def prepare_detect_frame(temp_vision_frame : VisionFrame, face_detector_size : s
 	face_detector_width, face_detector_height = unpack_resolution(face_detector_size)
 	detect_vision_frame = numpy.zeros((face_detector_height, face_detector_width, 3))
 	detect_vision_frame[:temp_vision_frame.shape[0], :temp_vision_frame.shape[1], :] = temp_vision_frame
-	detect_vision_frame = (detect_vision_frame - 127.5) / 128.0
 	detect_vision_frame = numpy.expand_dims(detect_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
 	return detect_vision_frame
+
+
+def normalize_detect_frame(detect_vision_frame : VisionFrame, normalize_range : Sequence[int]) -> VisionFrame:
+	if normalize_range == [ -1, 1 ]:
+		return (detect_vision_frame - 127.5) / 128.0
+	if normalize_range == [ 0, 1 ]:
+		return detect_vision_frame / 255.0
+	return detect_vision_frame

facefusion/face_helper.py

@@ -5,9 +5,9 @@ import cv2
 import numpy
 from cv2.typing import Size
 
-from facefusion.typing import Anchors, Angle, BoundingBox, Distance, FaceDetectorModel, FaceLandmark5, FaceLandmark68, Mask, Matrix, Points, Scale, Score, Translation, VisionFrame, WarpTemplate, WarpTemplateSet
+from facefusion.types import Anchors, Angle, BoundingBox, Distance, FaceDetectorModel, FaceLandmark5, FaceLandmark68, Mask, Matrix, Points, Scale, Score, Translation, VisionFrame, WarpTemplate, WarpTemplateSet
 
-WARP_TEMPLATES : WarpTemplateSet =\
+WARP_TEMPLATE_SET : WarpTemplateSet =\
 {
 	'arcface_112_v1': numpy.array(
 	[
@@ -25,7 +25,7 @@ WARP_TEMPLATES : WarpTemplateSet =\
 		[ 0.37097589, 0.82469196 ],
 		[ 0.63151696, 0.82325089 ]
 	]),
-	'arcface_128_v2': numpy.array(
+	'arcface_128': numpy.array(
 	[
 		[ 0.36167656, 0.40387734 ],
 		[ 0.63696719, 0.40235469 ],
@@ -33,6 +33,14 @@ WARP_TEMPLATES : WarpTemplateSet =\
 		[ 0.38710391, 0.72160547 ],
 		[ 0.61507734, 0.72034453 ]
 	]),
+	'dfl_whole_face': numpy.array(
+	[
+		[ 0.35342266, 0.39285716 ],
+		[ 0.62797622, 0.39285716 ],
+		[ 0.48660713, 0.54017860 ],
+		[ 0.38839287, 0.68750011 ],
+		[ 0.59821427, 0.68750011 ]
+	]),
 	'ffhq_512': numpy.array(
 	[
 		[ 0.37691676, 0.46864664 ],
@@ -40,12 +48,28 @@ WARP_TEMPLATES : WarpTemplateSet =\
 		[ 0.50123859, 0.61331904 ],
 		[ 0.39308822, 0.72541100 ],
 		[ 0.61150205, 0.72490465 ]
+	]),
+	'mtcnn_512': numpy.array(
+	[
+		[ 0.36562865, 0.46733799 ],
+		[ 0.63305391, 0.46585885 ],
+		[ 0.50019127, 0.61942959 ],
+		[ 0.39032951, 0.77598822 ],
+		[ 0.61178945, 0.77476328 ]
+	]),
+	'styleganex_384': numpy.array(
+	[
+		[ 0.42353745, 0.52289879 ],
+		[ 0.57725008, 0.52319972 ],
+		[ 0.50123859, 0.61331904 ],
+		[ 0.43364461, 0.68337652 ],
+		[ 0.57015325, 0.68306005 ]
 	])
 }
 
 
 def estimate_matrix_by_face_landmark_5(face_landmark_5 : FaceLandmark5, warp_template : WarpTemplate, crop_size : Size) -> Matrix:
-	normed_warp_template = WARP_TEMPLATES.get(warp_template) * crop_size
+	normed_warp_template = WARP_TEMPLATE_SET.get(warp_template) * crop_size
 	affine_matrix = cv2.estimateAffinePartial2D(face_landmark_5, normed_warp_template, method = cv2.RANSAC, ransacReprojThreshold = 100)[0]
 	return affine_matrix
 
@@ -75,15 +99,35 @@ def warp_face_by_translation(temp_vision_frame : VisionFrame, translation : Tran
 
 
 def paste_back(temp_vision_frame : VisionFrame, crop_vision_frame : VisionFrame, crop_mask : Mask, affine_matrix : Matrix) -> VisionFrame:
+	paste_bounding_box, paste_matrix = calc_paste_area(temp_vision_frame, crop_vision_frame, affine_matrix)
+	x_min, y_min, x_max, y_max = paste_bounding_box
+	paste_width = x_max - x_min
+	paste_height = y_max - y_min
+	inverse_mask = cv2.warpAffine(crop_mask, paste_matrix, (paste_width, paste_height)).clip(0, 1)
+	inverse_mask = numpy.expand_dims(inverse_mask, axis = -1)
+	inverse_vision_frame = cv2.warpAffine(crop_vision_frame, paste_matrix, (paste_width, paste_height), borderMode = cv2.BORDER_REPLICATE)
+	temp_vision_frame = temp_vision_frame.copy()
+	paste_vision_frame = temp_vision_frame[y_min:y_max, x_min:x_max]
+	paste_vision_frame = paste_vision_frame * (1 - inverse_mask) + inverse_vision_frame * inverse_mask
+	temp_vision_frame[y_min:y_max, x_min:x_max] = paste_vision_frame.astype(temp_vision_frame.dtype)
+	return temp_vision_frame
+
+
+def calc_paste_area(temp_vision_frame : VisionFrame, crop_vision_frame : VisionFrame, affine_matrix : Matrix) -> Tuple[BoundingBox, Matrix]:
+	temp_height, temp_width = temp_vision_frame.shape[:2]
+	crop_height, crop_width = crop_vision_frame.shape[:2]
 	inverse_matrix = cv2.invertAffineTransform(affine_matrix)
-	temp_size = temp_vision_frame.shape[:2][::-1]
-	inverse_mask = cv2.warpAffine(crop_mask, inverse_matrix, temp_size).clip(0, 1)
-	inverse_vision_frame = cv2.warpAffine(crop_vision_frame, inverse_matrix, temp_size, borderMode = cv2.BORDER_REPLICATE)
-	paste_vision_frame = temp_vision_frame.copy()
-	paste_vision_frame[:, :, 0] = inverse_mask * inverse_vision_frame[:, :, 0] + (1 - inverse_mask) * temp_vision_frame[:, :, 0]
-	paste_vision_frame[:, :, 1] = inverse_mask * inverse_vision_frame[:, :, 1] + (1 - inverse_mask) * temp_vision_frame[:, :, 1]
-	paste_vision_frame[:, :, 2] = inverse_mask * inverse_vision_frame[:, :, 2] + (1 - inverse_mask) * temp_vision_frame[:, :, 2]
-	return paste_vision_frame
+	crop_points = numpy.array([ [ 0, 0 ], [ crop_width, 0 ], [ crop_width, crop_height ], [ 0, crop_height ] ])
+	paste_region_points = transform_points(crop_points, inverse_matrix)
+	min_point = numpy.floor(paste_region_points.min(axis = 0)).astype(int)
+	max_point = numpy.ceil(paste_region_points.max(axis = 0)).astype(int)
+	x_min, y_min = numpy.clip(min_point, 0, [ temp_width, temp_height ])
+	x_max, y_max = numpy.clip(max_point, 0, [ temp_width, temp_height ])
+	paste_bounding_box = numpy.array([ x_min, y_min, x_max, y_max ])
+	paste_matrix = inverse_matrix.copy()
+	paste_matrix[0, 2] -= x_min
+	paste_matrix[1, 2] -= y_min
+	return paste_bounding_box, paste_matrix
 
 
 @lru_cache(maxsize = None)
@@ -184,9 +228,9 @@ def estimate_face_angle(face_landmark_68 : FaceLandmark68) -> Angle:
 	return face_angle
 
 
-def apply_nms(bounding_boxes : List[BoundingBox], face_scores : List[Score], score_threshold : float, nms_threshold : float) -> Sequence[int]:
+def apply_nms(bounding_boxes : List[BoundingBox], scores : List[Score], score_threshold : float, nms_threshold : float) -> Sequence[int]:
 	normed_bounding_boxes = [ (x1, y1, x2 - x1, y2 - y1) for (x1, y1, x2, y2) in bounding_boxes ]
-	keep_indices = cv2.dnn.NMSBoxes(normed_bounding_boxes, face_scores, score_threshold = score_threshold, nms_threshold = nms_threshold)
+	keep_indices = cv2.dnn.NMSBoxes(normed_bounding_boxes, scores, score_threshold = score_threshold, nms_threshold = nms_threshold)
 	return keep_indices
 
 

facefusion/face_landmarker.py

@@ -1,117 +1,121 @@
+from functools import lru_cache
 from typing import Tuple
 
 import cv2
 import numpy
 
 from facefusion import inference_manager, state_manager
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_helper import create_rotated_matrix_and_size, estimate_matrix_by_face_landmark_5, transform_points, warp_face_by_translation
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import Angle, BoundingBox, DownloadSet, FaceLandmark5, FaceLandmark68, InferencePool, ModelSet, Prediction, Score, VisionFrame
+from facefusion.types import Angle, BoundingBox, DownloadScope, DownloadSet, FaceLandmark5, FaceLandmark68, InferencePool, ModelSet, Prediction, Score, VisionFrame
 
-MODEL_SET : ModelSet =\
-{
-	'2dfan4':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'2dfan4':
 		{
-			'2dfan4':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/2dfan4.hash',
-				'path': resolve_relative_path('../.assets/models/2dfan4.hash')
-			}
+				'2dfan4':
+				{
+					'url': resolve_download_url('models-3.0.0', '2dfan4.hash'),
+					'path': resolve_relative_path('../.assets/models/2dfan4.hash')
+				}
+			},
+			'sources':
+			{
+				'2dfan4':
+				{
+					'url': resolve_download_url('models-3.0.0', '2dfan4.onnx'),
+					'path': resolve_relative_path('../.assets/models/2dfan4.onnx')
+				}
+			},
+			'size': (256, 256)
 		},
-		'sources':
+		'peppa_wutz':
 		{
-			'2dfan4':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/2dfan4.onnx',
-				'path': resolve_relative_path('../.assets/models/2dfan4.onnx')
-			}
+				'peppa_wutz':
+				{
+					'url': resolve_download_url('models-3.0.0', 'peppa_wutz.hash'),
+					'path': resolve_relative_path('../.assets/models/peppa_wutz.hash')
+				}
+			},
+			'sources':
+			{
+				'peppa_wutz':
+				{
+					'url': resolve_download_url('models-3.0.0', 'peppa_wutz.onnx'),
+					'path': resolve_relative_path('../.assets/models/peppa_wutz.onnx')
+				}
+			},
+			'size': (256, 256)
 		},
-		'size': (256, 256)
-	},
-	'peppa_wutz':
-	{
-		'hashes':
+		'fan_68_5':
 		{
-			'peppa_wutz':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/peppa_wutz.hash',
-				'path': resolve_relative_path('../.assets/models/peppa_wutz.hash')
-			}
-		},
-		'sources':
-		{
-			'peppa_wutz':
+				'fan_68_5':
+				{
+					'url': resolve_download_url('models-3.0.0', 'fan_68_5.hash'),
+					'path': resolve_relative_path('../.assets/models/fan_68_5.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/peppa_wutz.onnx',
-				'path': resolve_relative_path('../.assets/models/peppa_wutz.onnx')
-			}
-		},
-		'size': (256, 256)
-	},
-	'fan_68_5':
-	{
-		'hashes':
-		{
-			'fan_68_5':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/fan_68_5.hash',
-				'path': resolve_relative_path('../.assets/models/fan_68_5.hash')
-			}
-		},
-		'sources':
-		{
-			'fan_68_5':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/fan_68_5.onnx',
-				'path': resolve_relative_path('../.assets/models/fan_68_5.onnx')
+				'fan_68_5':
+				{
+					'url': resolve_download_url('models-3.0.0', 'fan_68_5.onnx'),
+					'path': resolve_relative_path('../.assets/models/fan_68_5.onnx')
+				}
 			}
 		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	_, model_sources = collect_model_downloads()
-	model_context = __name__ + '.' + state_manager.get_item('face_landmarker_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('face_landmarker_model'), 'fan_68_5' ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('face_landmarker_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ state_manager.get_item('face_landmarker_model'), 'fan_68_5' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
-	model_hashes =\
+	model_set = create_static_model_set('full')
+	model_hash_set =\
 	{
-		'fan_68_5': MODEL_SET.get('fan_68_5').get('hashes').get('fan_68_5')
+		'fan_68_5': model_set.get('fan_68_5').get('hashes').get('fan_68_5')
 	}
-	model_sources =\
+	model_source_set =\
 	{
-		'fan_68_5': MODEL_SET.get('fan_68_5').get('sources').get('fan_68_5')
+		'fan_68_5': model_set.get('fan_68_5').get('sources').get('fan_68_5')
 	}
 
-	if state_manager.get_item('face_landmarker_model') in [ 'many', '2dfan4' ]:
-		model_hashes['2dfan4'] = MODEL_SET.get('2dfan4').get('hashes').get('2dfan4')
-		model_sources['2dfan4'] = MODEL_SET.get('2dfan4').get('sources').get('2dfan4')
-	if state_manager.get_item('face_landmarker_model') in [ 'many', 'peppa_wutz' ]:
-		model_hashes['peppa_wutz'] = MODEL_SET.get('peppa_wutz').get('hashes').get('peppa_wutz')
-		model_sources['peppa_wutz'] = MODEL_SET.get('peppa_wutz').get('sources').get('peppa_wutz')
-	return model_hashes, model_sources
+	for face_landmarker_model in [ '2dfan4', 'peppa_wutz' ]:
+		if state_manager.get_item('face_landmarker_model') in [ 'many', face_landmarker_model ]:
+			model_hash_set[face_landmarker_model] = model_set.get(face_landmarker_model).get('hashes').get(face_landmarker_model)
+			model_source_set[face_landmarker_model] = model_set.get(face_landmarker_model).get('sources').get(face_landmarker_model)
+
+	return model_hash_set, model_source_set
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes, model_sources = collect_model_downloads()
+	model_hash_set, model_source_set = collect_model_downloads()
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
-def detect_face_landmarks(vision_frame : VisionFrame, bounding_box : BoundingBox, face_angle : Angle) -> Tuple[FaceLandmark68, Score]:
+def detect_face_landmark(vision_frame : VisionFrame, bounding_box : BoundingBox, face_angle : Angle) -> Tuple[FaceLandmark68, Score]:
 	face_landmark_2dfan4 = None
 	face_landmark_peppa_wutz = None
 	face_landmark_score_2dfan4 = 0.0
@@ -119,6 +123,7 @@ def detect_face_landmarks(vision_frame : VisionFrame, bounding_box : BoundingBox
 
 	if state_manager.get_item('face_landmarker_model') in [ 'many', '2dfan4' ]:
 		face_landmark_2dfan4, face_landmark_score_2dfan4 = detect_with_2dfan4(vision_frame, bounding_box, face_angle)
+
 	if state_manager.get_item('face_landmarker_model') in [ 'many', 'peppa_wutz' ]:
 		face_landmark_peppa_wutz, face_landmark_score_peppa_wutz = detect_with_peppa_wutz(vision_frame, bounding_box, face_angle)
 
@@ -128,7 +133,7 @@ def detect_face_landmarks(vision_frame : VisionFrame, bounding_box : BoundingBox
 
 
 def detect_with_2dfan4(temp_vision_frame: VisionFrame, bounding_box: BoundingBox, face_angle: Angle) -> Tuple[FaceLandmark68, Score]:
-	model_size = MODEL_SET.get('2dfan4').get('size')
+	model_size = create_static_model_set('full').get('2dfan4').get('size')
 	scale = 195 / numpy.subtract(bounding_box[2:], bounding_box[:2]).max().clip(1, None)
 	translation = (model_size[0] - numpy.add(bounding_box[2:], bounding_box[:2]) * scale) * 0.5
 	rotated_matrix, rotated_size = create_rotated_matrix_and_size(face_angle, model_size)
@@ -147,7 +152,7 @@ def detect_with_2dfan4(temp_vision_frame: VisionFrame, bounding_box: BoundingBox
 
 
 def detect_with_peppa_wutz(temp_vision_frame : VisionFrame, bounding_box : BoundingBox, face_angle : Angle) -> Tuple[FaceLandmark68, Score]:
-	model_size = MODEL_SET.get('peppa_wutz').get('size')
+	model_size = create_static_model_set('full').get('peppa_wutz').get('size')
 	scale = 195 / numpy.subtract(bounding_box[2:], bounding_box[:2]).max().clip(1, None)
 	translation = (model_size[0] - numpy.add(bounding_box[2:], bounding_box[:2]) * scale) * 0.5
 	rotated_matrix, rotated_size = create_rotated_matrix_and_size(face_angle, model_size)
@@ -167,7 +172,7 @@ def detect_with_peppa_wutz(temp_vision_frame : VisionFrame, bounding_box : Bound
 
 def conditional_optimize_contrast(crop_vision_frame : VisionFrame) -> VisionFrame:
 	crop_vision_frame = cv2.cvtColor(crop_vision_frame, cv2.COLOR_RGB2Lab)
-	if numpy.mean(crop_vision_frame[:, :, 0]) < 30: # type:ignore[arg-type]
+	if numpy.mean(crop_vision_frame[:, :, 0]) < 30: #type:ignore[arg-type]
 		crop_vision_frame[:, :, 0] = cv2.createCLAHE(clipLimit = 2).apply(crop_vision_frame[:, :, 0])
 	crop_vision_frame = cv2.cvtColor(crop_vision_frame, cv2.COLOR_Lab2RGB)
 	return crop_vision_frame

facefusion/face_masker.py

@@ -1,106 +1,162 @@
 from functools import lru_cache
-from typing import Dict, List, Tuple
+from typing import List, Tuple
 
 import cv2
 import numpy
-from cv2.typing import Size
 
-from facefusion import inference_manager
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+import facefusion.choices
+from facefusion import inference_manager, state_manager
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import DownloadSet, FaceLandmark68, FaceMaskRegion, InferencePool, Mask, ModelSet, Padding, VisionFrame
-
-MODEL_SET : ModelSet =\
-{
-	'face_occluder':
-	{
-		'hashes':
-		{
-			'face_occluder':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/dfl_xseg.hash',
-				'path': resolve_relative_path('../.assets/models/dfl_xseg.hash')
-			}
-		},
-		'sources':
-		{
-			'face_occluder':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/dfl_xseg.onnx',
-				'path': resolve_relative_path('../.assets/models/dfl_xseg.onnx')
-			}
-		},
-		'size': (256, 256)
-	},
-	'face_parser':
-	{
-		'hashes':
-		{
-			'face_parser':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/bisenet_resnet_34.hash',
-				'path': resolve_relative_path('../.assets/models/bisenet_resnet_34.hash')
-			}
-		},
-		'sources':
-		{
-			'face_parser':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/bisenet_resnet_34.onnx',
-				'path': resolve_relative_path('../.assets/models/bisenet_resnet_34.onnx')
-			}
-		},
-		'size': (512, 512)
-	}
-}
-FACE_MASK_REGIONS : Dict[FaceMaskRegion, int] =\
-{
-	'skin': 1,
-	'left-eyebrow': 2,
-	'right-eyebrow': 3,
-	'left-eye': 4,
-	'right-eye': 5,
-	'glasses': 6,
-	'nose': 10,
-	'mouth': 11,
-	'upper-lip': 12,
-	'lower-lip': 13
-}
-
-
-def get_inference_pool() -> InferencePool:
-	_, model_sources = collect_model_downloads()
-	return inference_manager.get_inference_pool(__name__, model_sources)
-
-
-def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
-
-
-def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
-	model_hashes =\
-	{
-		'face_occluder': MODEL_SET.get('face_occluder').get('hashes').get('face_occluder'),
-		'face_parser': MODEL_SET.get('face_parser').get('hashes').get('face_parser')
-	}
-	model_sources =\
-	{
-		'face_occluder': MODEL_SET.get('face_occluder').get('sources').get('face_occluder'),
-		'face_parser': MODEL_SET.get('face_parser').get('sources').get('face_parser')
-	}
-	return model_hashes, model_sources
-
-
-def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes, model_sources = collect_model_downloads()
-
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+from facefusion.types import DownloadScope, DownloadSet, FaceLandmark68, FaceMaskArea, FaceMaskRegion, InferencePool, Mask, ModelSet, Padding, VisionFrame
 
 
 @lru_cache(maxsize = None)
-def create_static_box_mask(crop_size : Size, face_mask_blur : float, face_mask_padding : Padding) -> Mask:
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
+	{
+		'xseg_1':
+		{
+			'hashes':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.1.0', 'xseg_1.hash'),
+					'path': resolve_relative_path('../.assets/models/xseg_1.hash')
+				}
+			},
+			'sources':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.1.0', 'xseg_1.onnx'),
+					'path': resolve_relative_path('../.assets/models/xseg_1.onnx')
+				}
+			},
+			'size': (256, 256)
+		},
+		'xseg_2':
+		{
+			'hashes':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.1.0', 'xseg_2.hash'),
+					'path': resolve_relative_path('../.assets/models/xseg_2.hash')
+				}
+			},
+			'sources':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.1.0', 'xseg_2.onnx'),
+					'path': resolve_relative_path('../.assets/models/xseg_2.onnx')
+				}
+			},
+			'size': (256, 256)
+		},
+		'xseg_3':
+		{
+			'hashes':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.2.0', 'xseg_3.hash'),
+					'path': resolve_relative_path('../.assets/models/xseg_3.hash')
+				}
+			},
+			'sources':
+			{
+				'face_occluder':
+				{
+					'url': resolve_download_url('models-3.2.0', 'xseg_3.onnx'),
+					'path': resolve_relative_path('../.assets/models/xseg_3.onnx')
+				}
+			},
+			'size': (256, 256)
+		},
+		'bisenet_resnet_18':
+		{
+			'hashes':
+			{
+				'face_parser':
+				{
+					'url': resolve_download_url('models-3.1.0', 'bisenet_resnet_18.hash'),
+					'path': resolve_relative_path('../.assets/models/bisenet_resnet_18.hash')
+				}
+			},
+			'sources':
+			{
+				'face_parser':
+				{
+					'url': resolve_download_url('models-3.1.0', 'bisenet_resnet_18.onnx'),
+					'path': resolve_relative_path('../.assets/models/bisenet_resnet_18.onnx')
+				}
+			},
+			'size': (512, 512)
+		},
+		'bisenet_resnet_34':
+		{
+			'hashes':
+			{
+				'face_parser':
+				{
+					'url': resolve_download_url('models-3.0.0', 'bisenet_resnet_34.hash'),
+					'path': resolve_relative_path('../.assets/models/bisenet_resnet_34.hash')
+				}
+			},
+			'sources':
+			{
+				'face_parser':
+				{
+					'url': resolve_download_url('models-3.0.0', 'bisenet_resnet_34.onnx'),
+					'path': resolve_relative_path('../.assets/models/bisenet_resnet_34.onnx')
+				}
+			},
+			'size': (512, 512)
+		}
+	}
+
+
+def get_inference_pool() -> InferencePool:
+	model_names = [ state_manager.get_item('face_occluder_model'), state_manager.get_item('face_parser_model') ]
+	_, model_source_set = collect_model_downloads()
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
+
+
+def clear_inference_pool() -> None:
+	model_names = [ state_manager.get_item('face_occluder_model'), state_manager.get_item('face_parser_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
+
+
+def collect_model_downloads() -> Tuple[DownloadSet, DownloadSet]:
+	model_set = create_static_model_set('full')
+	model_hash_set = {}
+	model_source_set = {}
+
+	for face_occluder_model in [ 'xseg_1', 'xseg_2', 'xseg_3' ]:
+		if state_manager.get_item('face_occluder_model') == face_occluder_model:
+			model_hash_set[face_occluder_model] = model_set.get(face_occluder_model).get('hashes').get('face_occluder')
+			model_source_set[face_occluder_model] = model_set.get(face_occluder_model).get('sources').get('face_occluder')
+
+	for face_parser_model in [ 'bisenet_resnet_18', 'bisenet_resnet_34' ]:
+		if state_manager.get_item('face_parser_model') == face_parser_model:
+			model_hash_set[face_parser_model] = model_set.get(face_parser_model).get('hashes').get('face_parser')
+			model_source_set[face_parser_model] = model_set.get(face_parser_model).get('sources').get('face_parser')
+
+	return model_hash_set, model_source_set
+
+
+def pre_check() -> bool:
+	model_hash_set, model_source_set = collect_model_downloads()
+
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
+
+
+def create_box_mask(crop_vision_frame : VisionFrame, face_mask_blur : float, face_mask_padding : Padding) -> Mask:
+	crop_size = crop_vision_frame.shape[:2][::-1]
 	blur_amount = int(crop_size[0] * 0.5 * face_mask_blur)
 	blur_area = max(blur_amount // 2, 1)
 	box_mask : Mask = numpy.ones(crop_size).astype(numpy.float32)
@@ -108,15 +164,17 @@ def create_static_box_mask(crop_size : Size, face_mask_blur : float, face_mask_p
 	box_mask[-max(blur_area, int(crop_size[1] * face_mask_padding[2] / 100)):, :] = 0
 	box_mask[:, :max(blur_area, int(crop_size[0] * face_mask_padding[3] / 100))] = 0
 	box_mask[:, -max(blur_area, int(crop_size[0] * face_mask_padding[1] / 100)):] = 0
+
 	if blur_amount > 0:
 		box_mask = cv2.GaussianBlur(box_mask, (0, 0), blur_amount * 0.25)
 	return box_mask
 
 
 def create_occlusion_mask(crop_vision_frame : VisionFrame) -> Mask:
-	model_size = MODEL_SET.get('face_occluder').get('size')
+	model_name = state_manager.get_item('face_occluder_model')
+	model_size = create_static_model_set('full').get(model_name).get('size')
 	prepare_vision_frame = cv2.resize(crop_vision_frame, model_size)
-	prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0).astype(numpy.float32) / 255
+	prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0).astype(numpy.float32) / 255.0
 	prepare_vision_frame = prepare_vision_frame.transpose(0, 1, 2, 3)
 	occlusion_mask = forward_occlude_face(prepare_vision_frame)
 	occlusion_mask = occlusion_mask.transpose(0, 1, 2).clip(0, 1).astype(numpy.float32)
@@ -125,32 +183,40 @@ def create_occlusion_mask(crop_vision_frame : VisionFrame) -> Mask:
 	return occlusion_mask
 
 
+def create_area_mask(crop_vision_frame : VisionFrame, face_landmark_68 : FaceLandmark68, face_mask_areas : List[FaceMaskArea]) -> Mask:
+	crop_size = crop_vision_frame.shape[:2][::-1]
+	landmark_points = []
+
+	for face_mask_area in face_mask_areas:
+		if face_mask_area in facefusion.choices.face_mask_area_set:
+			landmark_points.extend(facefusion.choices.face_mask_area_set.get(face_mask_area))
+
+	convex_hull = cv2.convexHull(face_landmark_68[landmark_points].astype(numpy.int32))
+	area_mask = numpy.zeros(crop_size).astype(numpy.float32)
+	cv2.fillConvexPoly(area_mask, convex_hull, 1.0) # type: ignore[call-overload]
+	area_mask = (cv2.GaussianBlur(area_mask.clip(0, 1), (0, 0), 5).clip(0.5, 1) - 0.5) * 2
+	return area_mask
+
+
 def create_region_mask(crop_vision_frame : VisionFrame, face_mask_regions : List[FaceMaskRegion]) -> Mask:
-	model_size = MODEL_SET.get('face_parser').get('size')
+	model_name = state_manager.get_item('face_parser_model')
+	model_size = create_static_model_set('full').get(model_name).get('size')
 	prepare_vision_frame = cv2.resize(crop_vision_frame, model_size)
-	prepare_vision_frame = prepare_vision_frame[:, :, ::-1].astype(numpy.float32) / 255
+	prepare_vision_frame = prepare_vision_frame[:, :, ::-1].astype(numpy.float32) / 255.0
 	prepare_vision_frame = numpy.subtract(prepare_vision_frame, numpy.array([ 0.485, 0.456, 0.406 ]).astype(numpy.float32))
 	prepare_vision_frame = numpy.divide(prepare_vision_frame, numpy.array([ 0.229, 0.224, 0.225 ]).astype(numpy.float32))
 	prepare_vision_frame = numpy.expand_dims(prepare_vision_frame, axis = 0)
 	prepare_vision_frame = prepare_vision_frame.transpose(0, 3, 1, 2)
 	region_mask = forward_parse_face(prepare_vision_frame)
-	region_mask = numpy.isin(region_mask.argmax(0), [ FACE_MASK_REGIONS[region] for region in face_mask_regions ])
+	region_mask = numpy.isin(region_mask.argmax(0), [ facefusion.choices.face_mask_region_set.get(face_mask_region) for face_mask_region in face_mask_regions ])
 	region_mask = cv2.resize(region_mask.astype(numpy.float32), crop_vision_frame.shape[:2][::-1])
 	region_mask = (cv2.GaussianBlur(region_mask.clip(0, 1), (0, 0), 5).clip(0.5, 1) - 0.5) * 2
 	return region_mask
 
 
-def create_mouth_mask(face_landmark_68 : FaceLandmark68) -> Mask:
-	convex_hull = cv2.convexHull(face_landmark_68[numpy.r_[3:14, 31:36]].astype(numpy.int32))
-	mouth_mask : Mask = numpy.zeros((512, 512)).astype(numpy.float32)
-	mouth_mask = cv2.fillConvexPoly(mouth_mask, convex_hull, 1.0) #type:ignore[call-overload]
-	mouth_mask = cv2.erode(mouth_mask.clip(0, 1), numpy.ones((21, 3)))
-	mouth_mask = cv2.GaussianBlur(mouth_mask, (0, 0), sigmaX = 1, sigmaY = 15)
-	return mouth_mask
-
-
 def forward_occlude_face(prepare_vision_frame : VisionFrame) -> Mask:
-	face_occluder = get_inference_pool().get('face_occluder')
+	model_name = state_manager.get_item('face_occluder_model')
+	face_occluder = get_inference_pool().get(model_name)
 
 	with conditional_thread_semaphore():
 		occlusion_mask : Mask = face_occluder.run(None,
@@ -162,7 +228,8 @@ def forward_occlude_face(prepare_vision_frame : VisionFrame) -> Mask:
 
 
 def forward_parse_face(prepare_vision_frame : VisionFrame) -> Mask:
-	face_parser = get_inference_pool().get('face_parser')
+	model_name = state_manager.get_item('face_parser_model')
+	face_parser = get_inference_pool().get(model_name)
 
 	with conditional_thread_semaphore():
 		region_mask : Mask = face_parser.run(None,

facefusion/face_recognizer.py

@@ -1,59 +1,65 @@
+from functools import lru_cache
 from typing import Tuple
 
 import numpy
 
 from facefusion import inference_manager
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_helper import warp_face_by_face_landmark_5
 from facefusion.filesystem import resolve_relative_path
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import Embedding, FaceLandmark5, InferencePool, ModelOptions, ModelSet, VisionFrame
+from facefusion.types import DownloadScope, Embedding, FaceLandmark5, InferencePool, ModelOptions, ModelSet, VisionFrame
 
-MODEL_SET : ModelSet =\
-{
-	'arcface':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'arcface':
 		{
-			'face_recognizer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_w600k_r50.hash',
-				'path': resolve_relative_path('../.assets/models/arcface_w600k_r50.hash')
-			}
-		},
-		'sources':
-		{
-			'face_recognizer':
+				'face_recognizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_w600k_r50.hash'),
+					'path': resolve_relative_path('../.assets/models/arcface_w600k_r50.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_w600k_r50.onnx',
-				'path': resolve_relative_path('../.assets/models/arcface_w600k_r50.onnx')
-			}
-		},
-		'template': 'arcface_112_v2',
-		'size': (112, 112)
+				'face_recognizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_w600k_r50.onnx'),
+					'path': resolve_relative_path('../.assets/models/arcface_w600k_r50.onnx')
+				}
+			},
+			'template': 'arcface_112_v2',
+			'size': (112, 112)
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	return inference_manager.get_inference_pool(__name__, model_sources)
+	model_names = [ 'arcface' ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ 'arcface' ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	return MODEL_SET.get('arcface')
+	return create_static_model_set('full').get('arcface')
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def calc_embedding(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5) -> Tuple[Embedding, Embedding]:

facefusion/face_selector.py

@@ -3,7 +3,7 @@ from typing import List
 import numpy
 
 from facefusion import state_manager
-from facefusion.typing import Face, FaceSelectorOrder, FaceSet, Gender, Race
+from facefusion.types import Face, FaceSelectorOrder, FaceSet, Gender, Race, Score
 
 
 def find_similar_faces(faces : List[Face], reference_faces : FaceSet, face_distance : float) -> List[Face]:
@@ -21,6 +21,7 @@ def find_similar_faces(faces : List[Face], reference_faces : FaceSet, face_dista
 
 def compare_faces(face : Face, reference_face : Face, face_distance : float) -> bool:
 	current_face_distance = calc_face_distance(face, reference_face)
+	current_face_distance = float(numpy.interp(current_face_distance, [ 0, 2 ], [ 0, 1 ]))
 	return current_face_distance < face_distance
 
 
@@ -33,37 +34,53 @@ def calc_face_distance(face : Face, reference_face : Face) -> float:
 def sort_and_filter_faces(faces : List[Face]) -> List[Face]:
 	if faces:
 		if state_manager.get_item('face_selector_order'):
-			faces = sort_by_order(faces, state_manager.get_item('face_selector_order'))
+			faces = sort_faces_by_order(faces, state_manager.get_item('face_selector_order'))
 		if state_manager.get_item('face_selector_gender'):
-			faces = filter_by_gender(faces, state_manager.get_item('face_selector_gender'))
+			faces = filter_faces_by_gender(faces, state_manager.get_item('face_selector_gender'))
 		if state_manager.get_item('face_selector_race'):
-			faces = filter_by_race(faces, state_manager.get_item('face_selector_race'))
+			faces = filter_faces_by_race(faces, state_manager.get_item('face_selector_race'))
 		if state_manager.get_item('face_selector_age_start') or state_manager.get_item('face_selector_age_end'):
-			faces = filter_by_age(faces, state_manager.get_item('face_selector_age_start'), state_manager.get_item('face_selector_age_end'))
+			faces = filter_faces_by_age(faces, state_manager.get_item('face_selector_age_start'), state_manager.get_item('face_selector_age_end'))
 	return faces
 
 
-def sort_by_order(faces : List[Face], order : FaceSelectorOrder) -> List[Face]:
+def sort_faces_by_order(faces : List[Face], order : FaceSelectorOrder) -> List[Face]:
 	if order == 'left-right':
-		return sorted(faces, key = lambda face: face.bounding_box[0])
+		return sorted(faces, key = get_bounding_box_left)
 	if order == 'right-left':
-		return sorted(faces, key = lambda face: face.bounding_box[0], reverse = True)
+		return sorted(faces, key = get_bounding_box_left, reverse = True)
 	if order == 'top-bottom':
-		return sorted(faces, key = lambda face: face.bounding_box[1])
+		return sorted(faces, key = get_bounding_box_top)
 	if order == 'bottom-top':
-		return sorted(faces, key = lambda face: face.bounding_box[1], reverse = True)
+		return sorted(faces, key = get_bounding_box_top, reverse = True)
 	if order == 'small-large':
-		return sorted(faces, key = lambda face: (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1]))
+		return sorted(faces, key = get_bounding_box_area)
 	if order == 'large-small':
-		return sorted(faces, key = lambda face: (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1]), reverse = True)
+		return sorted(faces, key = get_bounding_box_area, reverse = True)
 	if order == 'best-worst':
-		return sorted(faces, key = lambda face: face.score_set.get('detector'), reverse = True)
+		return sorted(faces, key = get_face_detector_score, reverse = True)
 	if order == 'worst-best':
-		return sorted(faces, key = lambda face: face.score_set.get('detector'))
+		return sorted(faces, key = get_face_detector_score)
 	return faces
 
 
-def filter_by_gender(faces : List[Face], gender : Gender) -> List[Face]:
+def get_bounding_box_left(face : Face) -> float:
+	return face.bounding_box[0]
+
+
+def get_bounding_box_top(face : Face) -> float:
+	return face.bounding_box[1]
+
+
+def get_bounding_box_area(face : Face) -> float:
+	return (face.bounding_box[2] - face.bounding_box[0]) * (face.bounding_box[3] - face.bounding_box[1])
+
+
+def get_face_detector_score(face : Face) -> Score:
+	return face.score_set.get('detector')
+
+
+def filter_faces_by_gender(faces : List[Face], gender : Gender) -> List[Face]:
 	filter_faces = []
 
 	for face in faces:
@@ -72,7 +89,7 @@ def filter_by_gender(faces : List[Face], gender : Gender) -> List[Face]:
 	return filter_faces
 
 
-def filter_by_age(faces : List[Face], face_selector_age_start : int, face_selector_age_end : int) -> List[Face]:
+def filter_faces_by_age(faces : List[Face], face_selector_age_start : int, face_selector_age_end : int) -> List[Face]:
 	filter_faces = []
 	age = range(face_selector_age_start, face_selector_age_end)
 
@@ -82,7 +99,7 @@ def filter_by_age(faces : List[Face], face_selector_age_start : int, face_select
 	return filter_faces
 
 
-def filter_by_race(faces : List[Face], race : Race) -> List[Face]:
+def filter_faces_by_race(faces : List[Face], race : Race) -> List[Face]:
 	filter_faces = []
 
 	for face in faces:

facefusion/face_store.py

@@ -1,9 +1,7 @@
-import hashlib
 from typing import List, Optional
 
-import numpy
-
-from facefusion.typing import Face, FaceSet, FaceStore, VisionFrame
+from facefusion.hash_helper import create_hash
+from facefusion.types import Face, FaceSet, FaceStore, VisionFrame
 
 FACE_STORE : FaceStore =\
 {
@@ -17,37 +15,29 @@ def get_face_store() -> FaceStore:
 
 
 def get_static_faces(vision_frame : VisionFrame) -> Optional[List[Face]]:
-	frame_hash = create_frame_hash(vision_frame)
-	if frame_hash in FACE_STORE['static_faces']:
-		return FACE_STORE['static_faces'][frame_hash]
-	return None
+	vision_hash = create_hash(vision_frame.tobytes())
+	return FACE_STORE.get('static_faces').get(vision_hash)
 
 
 def set_static_faces(vision_frame : VisionFrame, faces : List[Face]) -> None:
-	frame_hash = create_frame_hash(vision_frame)
-	if frame_hash:
-		FACE_STORE['static_faces'][frame_hash] = faces
+	vision_hash = create_hash(vision_frame.tobytes())
+	if vision_hash:
+		FACE_STORE['static_faces'][vision_hash] = faces
 
 
 def clear_static_faces() -> None:
-	FACE_STORE['static_faces'] = {}
-
-
-def create_frame_hash(vision_frame : VisionFrame) -> Optional[str]:
-	return hashlib.sha1(vision_frame.tobytes()).hexdigest() if numpy.any(vision_frame) else None
+	FACE_STORE['static_faces'].clear()
 
 
 def get_reference_faces() -> Optional[FaceSet]:
-	if FACE_STORE['reference_faces']:
-		return FACE_STORE['reference_faces']
-	return None
+	return FACE_STORE.get('reference_faces')
 
 
 def append_reference_face(name : str, face : Face) -> None:
-	if name not in FACE_STORE['reference_faces']:
+	if name not in FACE_STORE.get('reference_faces'):
 		FACE_STORE['reference_faces'][name] = []
 	FACE_STORE['reference_faces'][name].append(face)
 
 
 def clear_reference_faces() -> None:
-	FACE_STORE['reference_faces'] = {}
+	FACE_STORE['reference_faces'].clear()

facefusion/ffmpeg.py

@@ -1,26 +1,35 @@
 import os
-import shutil
 import subprocess
 import tempfile
-from typing import List, Optional
+from functools import partial
+from typing import List, Optional, cast
 
-import filetype
+from tqdm import tqdm
 
-from facefusion import logger, process_manager, state_manager
-from facefusion.filesystem import remove_file
+import facefusion.choices
+from facefusion import ffmpeg_builder, logger, process_manager, state_manager, wording
+from facefusion.filesystem import get_file_format, remove_file
 from facefusion.temp_helper import get_temp_file_path, get_temp_frames_pattern
-from facefusion.typing import AudioBuffer, Fps, OutputVideoPreset
-from facefusion.vision import restrict_video_fps
+from facefusion.types import AudioBuffer, AudioEncoder, Commands, EncoderSet, Fps, UpdateProgress, VideoEncoder, VideoFormat
+from facefusion.vision import detect_video_duration, detect_video_fps, predict_video_frame_total
 
 
-def run_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
-	commands = [ shutil.which('ffmpeg'), '-hide_banner', '-loglevel', 'error' ]
-	commands.extend(args)
+def run_ffmpeg_with_progress(commands : Commands, update_progress : UpdateProgress) -> subprocess.Popen[bytes]:
+	log_level = state_manager.get_item('log_level')
+	commands.extend(ffmpeg_builder.set_progress())
+	commands.extend(ffmpeg_builder.cast_stream())
+	commands = ffmpeg_builder.run(commands)
 	process = subprocess.Popen(commands, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
 
 	while process_manager.is_processing():
 		try:
-			if state_manager.get_item('log_level') == 'debug':
+
+			while __line__ := process.stdout.readline().decode().lower():
+				if 'frame=' in __line__:
+					_, frame_number = __line__.split('frame=')
+					update_progress(int(frame_number))
+
+			if log_level == 'debug':
 				log_debug(process)
 			process.wait(timeout = 0.5)
 		except subprocess.TimeoutExpired:
@@ -32,9 +41,31 @@ def run_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
 	return process
 
 
-def open_ffmpeg(args : List[str]) -> subprocess.Popen[bytes]:
-	commands = [ shutil.which('ffmpeg'), '-hide_banner', '-loglevel', 'quiet' ]
-	commands.extend(args)
+def update_progress(progress : tqdm, frame_number : int) -> None:
+	progress.update(frame_number - progress.n)
+
+
+def run_ffmpeg(commands : Commands) -> subprocess.Popen[bytes]:
+	log_level = state_manager.get_item('log_level')
+	commands = ffmpeg_builder.run(commands)
+	process = subprocess.Popen(commands, stderr = subprocess.PIPE, stdout = subprocess.PIPE)
+
+	while process_manager.is_processing():
+		try:
+			if log_level == 'debug':
+				log_debug(process)
+			process.wait(timeout = 0.5)
+		except subprocess.TimeoutExpired:
+			continue
+		return process
+
+	if process_manager.is_stopping():
+		process.terminate()
+	return process
+
+
+def open_ffmpeg(commands : Commands) -> subprocess.Popen[bytes]:
+	commands = ffmpeg_builder.run(commands)
 	return subprocess.Popen(commands, stdin = subprocess.PIPE, stdout = subprocess.PIPE)
 
 
@@ -47,48 +78,167 @@ def log_debug(process : subprocess.Popen[bytes]) -> None:
 			logger.debug(error.strip(), __name__)
 
 
-def extract_frames(target_path : str, temp_video_resolution : str, temp_video_fps : Fps) -> bool:
-	trim_frame_start = state_manager.get_item('trim_frame_start')
-	trim_frame_end = state_manager.get_item('trim_frame_end')
-	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
-	commands = [ '-i', target_path, '-s', str(temp_video_resolution), '-q:v', '0' ]
+def get_available_encoder_set() -> EncoderSet:
+	available_encoder_set : EncoderSet =\
+	{
+		'audio': [],
+		'video': []
+	}
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.get_encoders()
+	)
+	process = run_ffmpeg(commands)
 
-	if isinstance(trim_frame_start, int) and isinstance(trim_frame_end, int):
-		commands.extend([ '-vf', 'trim=start_frame=' + str(trim_frame_start) + ':end_frame=' + str(trim_frame_end) + ',fps=' + str(temp_video_fps) ])
-	elif isinstance(trim_frame_start, int):
-		commands.extend([ '-vf', 'trim=start_frame=' + str(trim_frame_start) + ',fps=' + str(temp_video_fps) ])
-	elif isinstance(trim_frame_end, int):
-		commands.extend([ '-vf', 'trim=end_frame=' + str(trim_frame_end) + ',fps=' + str(temp_video_fps) ])
-	else:
-		commands.extend([ '-vf', 'fps=' + str(temp_video_fps) ])
-	commands.extend([ '-vsync', '0', temp_frames_pattern ])
+	while line := process.stdout.readline().decode().lower():
+		if line.startswith(' a'):
+			audio_encoder = line.split()[1]
+
+			if audio_encoder in facefusion.choices.output_audio_encoders:
+				index = facefusion.choices.output_audio_encoders.index(audio_encoder) #type:ignore[arg-type]
+				available_encoder_set['audio'].insert(index, audio_encoder) #type:ignore[arg-type]
+		if line.startswith(' v'):
+			video_encoder = line.split()[1]
+
+			if video_encoder in facefusion.choices.output_video_encoders:
+				index = facefusion.choices.output_video_encoders.index(video_encoder) #type:ignore[arg-type]
+				available_encoder_set['video'].insert(index, video_encoder) #type:ignore[arg-type]
+
+	return available_encoder_set
+
+
+def extract_frames(target_path : str, temp_video_resolution : str, temp_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+	extract_frame_total = predict_video_frame_total(target_path, temp_video_fps, trim_frame_start, trim_frame_end)
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.set_media_resolution(temp_video_resolution),
+		ffmpeg_builder.set_frame_quality(0),
+		ffmpeg_builder.select_frame_range(trim_frame_start, trim_frame_end, temp_video_fps),
+		ffmpeg_builder.prevent_frame_drop(),
+		ffmpeg_builder.set_output(temp_frames_pattern)
+	)
+
+	with tqdm(total = extract_frame_total, desc = wording.get('extracting'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+		process = run_ffmpeg_with_progress(commands, partial(update_progress, progress))
+		return process.returncode == 0
+
+
+def copy_image(target_path : str, temp_image_resolution : str) -> bool:
+	temp_image_path = get_temp_file_path(target_path)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.set_media_resolution(temp_image_resolution),
+		ffmpeg_builder.set_image_quality(target_path, 100),
+		ffmpeg_builder.force_output(temp_image_path)
+	)
 	return run_ffmpeg(commands).returncode == 0
 
 
-def merge_video(target_path : str, output_video_resolution : str, output_video_fps : Fps) -> bool:
-	temp_video_fps = restrict_video_fps(target_path, output_video_fps)
-	temp_file_path = get_temp_file_path(target_path)
-	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
-	commands = [ '-r', str(temp_video_fps), '-i', temp_frames_pattern, '-s', str(output_video_resolution), '-c:v', state_manager.get_item('output_video_encoder') ]
-
-	if state_manager.get_item('output_video_encoder') in [ 'libx264', 'libx265' ]:
-		output_video_compression = round(51 - (state_manager.get_item('output_video_quality') * 0.51))
-		commands.extend([ '-crf', str(output_video_compression), '-preset', state_manager.get_item('output_video_preset') ])
-	if state_manager.get_item('output_video_encoder') in [ 'libvpx-vp9' ]:
-		output_video_compression = round(63 - (state_manager.get_item('output_video_quality') * 0.63))
-		commands.extend([ '-crf', str(output_video_compression) ])
-	if state_manager.get_item('output_video_encoder') in [ 'h264_nvenc', 'hevc_nvenc' ]:
-		output_video_compression = round(51 - (state_manager.get_item('output_video_quality') * 0.51))
-		commands.extend([ '-cq', str(output_video_compression), '-preset', map_nvenc_preset(state_manager.get_item('output_video_preset')) ])
-	if state_manager.get_item('output_video_encoder') in [ 'h264_amf', 'hevc_amf' ]:
-		output_video_compression = round(51 - (state_manager.get_item('output_video_quality') * 0.51))
-		commands.extend([ '-qp_i', str(output_video_compression), '-qp_p', str(output_video_compression), '-quality', map_amf_preset(state_manager.get_item('output_video_preset')) ])
-	if state_manager.get_item('output_video_encoder') in [ 'h264_videotoolbox', 'hevc_videotoolbox' ]:
-		commands.extend([ '-q:v', str(state_manager.get_item('output_video_quality')) ])
-	commands.extend([ '-vf', 'framerate=fps=' + str(output_video_fps), '-pix_fmt', 'yuv420p', '-colorspace', 'bt709', '-y', temp_file_path ])
+def finalize_image(target_path : str, output_path : str, output_image_resolution : str) -> bool:
+	output_image_quality = state_manager.get_item('output_image_quality')
+	temp_image_path = get_temp_file_path(target_path)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(temp_image_path),
+		ffmpeg_builder.set_media_resolution(output_image_resolution),
+		ffmpeg_builder.set_image_quality(target_path, output_image_quality),
+		ffmpeg_builder.force_output(output_path)
+	)
 	return run_ffmpeg(commands).returncode == 0
 
 
+def read_audio_buffer(target_path : str, audio_sample_rate : int, audio_sample_size : int, audio_channel_total : int) -> Optional[AudioBuffer]:
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.ignore_video_stream(),
+		ffmpeg_builder.set_audio_sample_rate(audio_sample_rate),
+		ffmpeg_builder.set_audio_sample_size(audio_sample_size),
+		ffmpeg_builder.set_audio_channel_total(audio_channel_total),
+		ffmpeg_builder.cast_stream()
+	)
+
+	process = open_ffmpeg(commands)
+	audio_buffer, _ = process.communicate()
+	if process.returncode == 0:
+		return audio_buffer
+	return None
+
+
+def restore_audio(target_path : str, output_path : str, trim_frame_start : int, trim_frame_end : int) -> bool:
+	output_audio_encoder = state_manager.get_item('output_audio_encoder')
+	output_audio_quality = state_manager.get_item('output_audio_quality')
+	output_audio_volume = state_manager.get_item('output_audio_volume')
+	target_video_fps = detect_video_fps(target_path)
+	temp_video_path = get_temp_file_path(target_path)
+	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_video_duration = detect_video_duration(temp_video_path)
+
+	output_audio_encoder = fix_audio_encoder(temp_video_format, output_audio_encoder)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(temp_video_path),
+		ffmpeg_builder.select_media_range(trim_frame_start, trim_frame_end, target_video_fps),
+		ffmpeg_builder.set_input(target_path),
+		ffmpeg_builder.copy_video_encoder(),
+		ffmpeg_builder.set_audio_encoder(output_audio_encoder),
+		ffmpeg_builder.set_audio_quality(output_audio_encoder, output_audio_quality),
+		ffmpeg_builder.set_audio_volume(output_audio_volume),
+		ffmpeg_builder.select_media_stream('0:v:0'),
+		ffmpeg_builder.select_media_stream('1:a:0'),
+		ffmpeg_builder.set_video_duration(temp_video_duration),
+		ffmpeg_builder.force_output(output_path)
+	)
+	return run_ffmpeg(commands).returncode == 0
+
+
+def replace_audio(target_path : str, audio_path : str, output_path : str) -> bool:
+	output_audio_encoder = state_manager.get_item('output_audio_encoder')
+	output_audio_quality = state_manager.get_item('output_audio_quality')
+	output_audio_volume = state_manager.get_item('output_audio_volume')
+	temp_video_path = get_temp_file_path(target_path)
+	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_video_duration = detect_video_duration(temp_video_path)
+
+	output_audio_encoder = fix_audio_encoder(temp_video_format, output_audio_encoder)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input(temp_video_path),
+		ffmpeg_builder.set_input(audio_path),
+		ffmpeg_builder.copy_video_encoder(),
+		ffmpeg_builder.set_audio_encoder(output_audio_encoder),
+		ffmpeg_builder.set_audio_quality(output_audio_encoder, output_audio_quality),
+		ffmpeg_builder.set_audio_volume(output_audio_volume),
+		ffmpeg_builder.set_video_duration(temp_video_duration),
+		ffmpeg_builder.force_output(output_path)
+	)
+	return run_ffmpeg(commands).returncode == 0
+
+
+def merge_video(target_path : str, temp_video_fps : Fps, output_video_resolution : str, output_video_fps : Fps, trim_frame_start : int, trim_frame_end : int) -> bool:
+	output_video_encoder = state_manager.get_item('output_video_encoder')
+	output_video_quality = state_manager.get_item('output_video_quality')
+	output_video_preset = state_manager.get_item('output_video_preset')
+	merge_frame_total = predict_video_frame_total(target_path, output_video_fps, trim_frame_start, trim_frame_end)
+	temp_video_path = get_temp_file_path(target_path)
+	temp_video_format = cast(VideoFormat, get_file_format(temp_video_path))
+	temp_frames_pattern = get_temp_frames_pattern(target_path, '%08d')
+
+	output_video_encoder = fix_video_encoder(temp_video_format, output_video_encoder)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.set_input_fps(temp_video_fps),
+		ffmpeg_builder.set_input(temp_frames_pattern),
+		ffmpeg_builder.set_media_resolution(output_video_resolution),
+		ffmpeg_builder.set_video_encoder(output_video_encoder),
+		ffmpeg_builder.set_video_quality(output_video_encoder, output_video_quality),
+		ffmpeg_builder.set_video_preset(output_video_encoder, output_video_preset),
+		ffmpeg_builder.set_video_fps(output_video_fps),
+		ffmpeg_builder.set_pixel_format(output_video_encoder),
+		ffmpeg_builder.set_video_colorspace('bt709'),
+		ffmpeg_builder.force_output(temp_video_path)
+	)
+
+	with tqdm(total = merge_frame_total, desc = wording.get('merging'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
+		process = run_ffmpeg_with_progress(commands, partial(update_progress, progress))
+		return process.returncode == 0
+
+
 def concat_video(output_path : str, temp_output_paths : List[str]) -> bool:
 	concat_video_path = tempfile.mktemp()
 
@@ -97,80 +247,40 @@ def concat_video(output_path : str, temp_output_paths : List[str]) -> bool:
 			concat_video_file.write('file \'' + os.path.abspath(temp_output_path) + '\'' + os.linesep)
 		concat_video_file.flush()
 		concat_video_file.close()
-	commands = [ '-f', 'concat', '-safe', '0', '-i', concat_video_file.name, '-c:v', 'copy', '-c:a', state_manager.get_item('output_audio_encoder'), '-y', os.path.abspath(output_path) ]
+
+	output_path = os.path.abspath(output_path)
+	commands = ffmpeg_builder.chain(
+		ffmpeg_builder.unsafe_concat(),
+		ffmpeg_builder.set_input(concat_video_file.name),
+		ffmpeg_builder.copy_video_encoder(),
+		ffmpeg_builder.copy_audio_encoder(),
+		ffmpeg_builder.force_output(output_path)
+	)
 	process = run_ffmpeg(commands)
 	process.communicate()
 	remove_file(concat_video_path)
 	return process.returncode == 0
 
 
-def copy_image(target_path : str, temp_image_resolution : str) -> bool:
-	temp_file_path = get_temp_file_path(target_path)
-	temp_image_compression = calc_image_compression(target_path, 100)
-	commands = [ '-i', target_path, '-s', str(temp_image_resolution), '-q:v', str(temp_image_compression), '-y', temp_file_path ]
-	return run_ffmpeg(commands).returncode == 0
+def fix_audio_encoder(video_format : VideoFormat, audio_encoder : AudioEncoder) -> AudioEncoder:
+	if video_format == 'avi' and audio_encoder == 'libopus':
+		return 'aac'
+	if video_format == 'm4v':
+		return 'aac'
+	if video_format == 'mov' and audio_encoder in [ 'flac', 'libopus' ]:
+		return 'aac'
+	if video_format == 'webm':
+		return 'libopus'
+	return audio_encoder
 
 
-def finalize_image(target_path : str, output_path : str, output_image_resolution : str) -> bool:
-	temp_file_path = get_temp_file_path(target_path)
-	output_image_compression = calc_image_compression(target_path, state_manager.get_item('output_image_quality'))
-	commands = [ '-i', temp_file_path, '-s', str(output_image_resolution), '-q:v', str(output_image_compression), '-y', output_path ]
-	return run_ffmpeg(commands).returncode == 0
-
-
-def calc_image_compression(image_path : str, image_quality : int) -> int:
-	is_webp = filetype.guess_mime(image_path) == 'image/webp'
-	if is_webp:
-		image_quality = 100 - image_quality
-	return round(31 - (image_quality * 0.31))
-
-
-def read_audio_buffer(target_path : str, sample_rate : int, channel_total : int) -> Optional[AudioBuffer]:
-	commands = [ '-i', target_path, '-vn', '-f', 's16le', '-acodec', 'pcm_s16le', '-ar', str(sample_rate), '-ac', str(channel_total), '-' ]
-	process = open_ffmpeg(commands)
-	audio_buffer, _ = process.communicate()
-	if process.returncode == 0:
-		return audio_buffer
-	return None
-
-
-def restore_audio(target_path : str, output_path : str, output_video_fps : Fps) -> bool:
-	trim_frame_start = state_manager.get_item('trim_frame_start')
-	trim_frame_end = state_manager.get_item('trim_frame_end')
-	temp_file_path = get_temp_file_path(target_path)
-	commands = [ '-i', temp_file_path ]
-
-	if isinstance(trim_frame_start, int):
-		start_time = trim_frame_start / output_video_fps
-		commands.extend([ '-ss', str(start_time) ])
-	if isinstance(trim_frame_end, int):
-		end_time = trim_frame_end / output_video_fps
-		commands.extend([ '-to', str(end_time) ])
-	commands.extend([ '-i', target_path, '-c:v', 'copy', '-c:a', state_manager.get_item('output_audio_encoder'), '-map', '0:v:0', '-map', '1:a:0', '-shortest', '-y', output_path ])
-	return run_ffmpeg(commands).returncode == 0
-
-
-def replace_audio(target_path : str, audio_path : str, output_path : str) -> bool:
-	temp_file_path = get_temp_file_path(target_path)
-	commands = [ '-i', temp_file_path, '-i', audio_path, '-c:a', state_manager.get_item('output_audio_encoder'), '-af', 'apad', '-shortest', '-y', output_path ]
-	return run_ffmpeg(commands).returncode == 0
-
-
-def map_nvenc_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
-	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast' ]:
-		return 'fast'
-	if output_video_preset == 'medium':
-		return 'medium'
-	if output_video_preset in [ 'slow', 'slower', 'veryslow' ]:
-		return 'slow'
-	return None
-
-
-def map_amf_preset(output_video_preset : OutputVideoPreset) -> Optional[str]:
-	if output_video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
-		return 'speed'
-	if output_video_preset in [ 'faster', 'fast', 'medium' ]:
-		return 'balanced'
-	if output_video_preset in [ 'slow', 'slower', 'veryslow' ]:
-		return 'quality'
-	return None
+def fix_video_encoder(video_format : VideoFormat, video_encoder : VideoEncoder) -> VideoEncoder:
+	if video_format == 'm4v':
+		return 'libx264'
+	if video_format in [ 'mkv', 'mp4' ] and video_encoder == 'rawvideo':
+		return 'libx264'
+	if video_format == 'mov' and video_encoder == 'libvpx-vp9':
+		return 'libx264'
+	if video_format == 'webm':
+		return 'libvpx-vp9'
+	return video_encoder

facefusion/ffmpeg_builder.py

@@ -0,0 +1,248 @@
+import itertools
+import shutil
+from typing import Optional
+
+import numpy
+
+from facefusion.filesystem import get_file_format
+from facefusion.types import AudioEncoder, Commands, Duration, Fps, StreamMode, VideoEncoder, VideoPreset
+
+
+def run(commands : Commands) -> Commands:
+	return [ shutil.which('ffmpeg'), '-loglevel', 'error' ] + commands
+
+
+def chain(*commands : Commands) -> Commands:
+	return list(itertools.chain(*commands))
+
+
+def get_encoders() -> Commands:
+	return [ '-encoders' ]
+
+
+def set_hardware_accelerator(value : str) -> Commands:
+	return [ '-hwaccel', value ]
+
+
+def set_progress() -> Commands:
+	return [ '-progress' ]
+
+
+def set_input(input_path : str) -> Commands:
+	return [ '-i', input_path ]
+
+
+def set_input_fps(input_fps : Fps) -> Commands:
+	return [ '-r', str(input_fps)]
+
+
+def set_output(output_path : str) -> Commands:
+	return [ output_path ]
+
+
+def force_output(output_path : str) -> Commands:
+	return [ '-y', output_path ]
+
+
+def cast_stream() -> Commands:
+	return [ '-' ]
+
+
+def set_stream_mode(stream_mode : StreamMode) -> Commands:
+	if stream_mode == 'udp':
+		return [ '-f', 'mpegts' ]
+	if stream_mode == 'v4l2':
+		return [ '-f', 'v4l2' ]
+	return []
+
+
+def set_stream_quality(stream_quality : int) -> Commands:
+	return [ '-b:v', str(stream_quality) + 'k' ]
+
+
+def unsafe_concat() -> Commands:
+	return [ '-f', 'concat', '-safe', '0' ]
+
+
+def set_pixel_format(video_encoder : VideoEncoder) -> Commands:
+	if video_encoder == 'rawvideo':
+		return [ '-pix_fmt', 'rgb24' ]
+	return [ '-pix_fmt', 'yuv420p' ]
+
+
+def set_frame_quality(frame_quality : int) -> Commands:
+	return [ '-q:v', str(frame_quality) ]
+
+
+def select_frame_range(frame_start : int, frame_end : int, video_fps : Fps) -> Commands:
+	if isinstance(frame_start, int) and isinstance(frame_end, int):
+		return [ '-vf', 'trim=start_frame=' + str(frame_start) + ':end_frame=' + str(frame_end) + ',fps=' + str(video_fps) ]
+	if isinstance(frame_start, int):
+		return [ '-vf', 'trim=start_frame=' + str(frame_start) + ',fps=' + str(video_fps) ]
+	if isinstance(frame_end, int):
+		return [ '-vf', 'trim=end_frame=' + str(frame_end) + ',fps=' + str(video_fps) ]
+	return [ '-vf', 'fps=' + str(video_fps) ]
+
+
+def prevent_frame_drop() -> Commands:
+	return [ '-vsync', '0' ]
+
+
+def select_media_range(frame_start : int, frame_end : int, media_fps : Fps) -> Commands:
+	commands = []
+
+	if isinstance(frame_start, int):
+		commands.extend([ '-ss', str(frame_start / media_fps) ])
+	if isinstance(frame_end, int):
+		commands.extend([ '-to', str(frame_end / media_fps) ])
+	return commands
+
+
+def select_media_stream(media_stream : str) -> Commands:
+	return [ '-map', media_stream ]
+
+
+def set_media_resolution(video_resolution : str) -> Commands:
+	return [ '-s', video_resolution ]
+
+
+def set_image_quality(image_path : str, image_quality : int) -> Commands:
+	if get_file_format(image_path) == 'webp':
+		image_compression = image_quality
+	else:
+		image_compression = round(31 - (image_quality * 0.31))
+	return [ '-q:v', str(image_compression) ]
+
+
+def set_audio_encoder(audio_codec : str) -> Commands:
+	return [ '-c:a', audio_codec ]
+
+
+def copy_audio_encoder() -> Commands:
+	return set_audio_encoder('copy')
+
+
+def set_audio_sample_rate(audio_sample_rate : int) -> Commands:
+	return [ '-ar', str(audio_sample_rate) ]
+
+
+def set_audio_sample_size(audio_sample_size : int) -> Commands:
+	if audio_sample_size == 16:
+		return [ '-f', 's16le' ]
+	if audio_sample_size == 32:
+		return [ '-f', 's32le' ]
+	return []
+
+
+def set_audio_channel_total(audio_channel_total : int) -> Commands:
+	return [ '-ac', str(audio_channel_total) ]
+
+
+def set_audio_quality(audio_encoder : AudioEncoder, audio_quality : int) -> Commands:
+	if audio_encoder == 'aac':
+		audio_compression = round(numpy.interp(audio_quality, [ 0, 100 ], [ 0.1, 2.0 ]), 1)
+		return [ '-q:a', str(audio_compression) ]
+	if audio_encoder == 'libmp3lame':
+		audio_compression = round(numpy.interp(audio_quality, [ 0, 100 ], [ 9, 0 ]))
+		return [ '-q:a', str(audio_compression) ]
+	if audio_encoder == 'libopus':
+		audio_bit_rate = round(numpy.interp(audio_quality, [ 0, 100 ], [ 64, 256 ]))
+		return [ '-b:a', str(audio_bit_rate) + 'k' ]
+	if audio_encoder == 'libvorbis':
+		audio_compression = round(numpy.interp(audio_quality, [ 0, 100 ], [ -1, 10 ]), 1)
+		return [ '-q:a', str(audio_compression) ]
+	return []
+
+
+def set_audio_volume(audio_volume : int) -> Commands:
+	return [ '-filter:a', 'volume=' + str(audio_volume / 100) ]
+
+
+def set_video_encoder(video_encoder : str) -> Commands:
+	return [ '-c:v', video_encoder ]
+
+
+def copy_video_encoder() -> Commands:
+	return set_video_encoder('copy')
+
+
+def set_video_quality(video_encoder : VideoEncoder, video_quality : int) -> Commands:
+	if video_encoder in [ 'libx264', 'libx265' ]:
+		video_compression = round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ]))
+		return [ '-crf', str(video_compression) ]
+	if video_encoder == 'libvpx-vp9':
+		video_compression = round(numpy.interp(video_quality, [ 0, 100 ], [ 63, 0 ]))
+		return [ '-crf', str(video_compression) ]
+	if video_encoder in [ 'h264_nvenc', 'hevc_nvenc' ]:
+		video_compression = round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ]))
+		return [ '-cq', str(video_compression) ]
+	if video_encoder in [ 'h264_amf', 'hevc_amf' ]:
+		video_compression = round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ]))
+		return [ '-qp_i', str(video_compression), '-qp_p', str(video_compression), '-qp_b', str(video_compression) ]
+	if video_encoder in [ 'h264_qsv', 'hevc_qsv' ]:
+		video_compression = round(numpy.interp(video_quality, [ 0, 100 ], [ 51, 0 ]))
+		return [ '-qp', str(video_compression) ]
+	if video_encoder in [ 'h264_videotoolbox', 'hevc_videotoolbox' ]:
+		video_bit_rate = round(numpy.interp(video_quality, [ 0, 100 ], [ 1024, 50512 ]))
+		return [ '-b:v', str(video_bit_rate) + 'k' ]
+	return []
+
+
+def set_video_preset(video_encoder : VideoEncoder, video_preset : VideoPreset) -> Commands:
+	if video_encoder in [ 'libx264', 'libx265' ]:
+		return [ '-preset', video_preset ]
+	if video_encoder in [ 'h264_nvenc', 'hevc_nvenc' ]:
+		return [ '-preset', map_nvenc_preset(video_preset) ]
+	if video_encoder in [ 'h264_amf', 'hevc_amf' ]:
+		return [ '-quality', map_amf_preset(video_preset) ]
+	if video_encoder in [ 'h264_qsv', 'hevc_qsv' ]:
+		return [ '-preset', map_qsv_preset(video_preset) ]
+	return []
+
+
+def set_video_colorspace(video_colorspace : str) -> Commands:
+	return [ '-colorspace', video_colorspace ]
+
+
+def set_video_fps(video_fps : Fps) -> Commands:
+	return [ '-vf', 'framerate=fps=' + str(video_fps) ]
+
+
+def set_video_duration(video_duration : Duration) -> Commands:
+	return [ '-t', str(video_duration) ]
+
+
+def capture_video() -> Commands:
+	return [ '-f', 'rawvideo', '-pix_fmt', 'rgb24' ]
+
+
+def ignore_video_stream() -> Commands:
+	return [ '-vn' ]
+
+
+def map_nvenc_preset(video_preset : VideoPreset) -> Optional[str]:
+	if video_preset in [ 'ultrafast', 'superfast', 'veryfast', 'faster', 'fast' ]:
+		return 'fast'
+	if video_preset == 'medium':
+		return 'medium'
+	if video_preset in [ 'slow', 'slower', 'veryslow' ]:
+		return 'slow'
+	return None
+
+
+def map_amf_preset(video_preset : VideoPreset) -> Optional[str]:
+	if video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
+		return 'speed'
+	if video_preset in [ 'faster', 'fast', 'medium' ]:
+		return 'balanced'
+	if video_preset in [ 'slow', 'slower', 'veryslow' ]:
+		return 'quality'
+	return None
+
+
+def map_qsv_preset(video_preset : VideoPreset) -> Optional[str]:
+	if video_preset in [ 'ultrafast', 'superfast', 'veryfast' ]:
+		return 'veryfast'
+	if video_preset in [ 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow' ]:
+		return video_preset
+	return None

facefusion/filesystem.py

@@ -1,14 +1,9 @@
+import glob
 import os
 import shutil
-from pathlib import Path
 from typing import List, Optional
 
-import filetype
-
-from facefusion.common_helper import is_windows
-
-if is_windows():
-	import ctypes
+import facefusion.choices
 
 
 def get_file_size(file_path : str) -> int:
@@ -17,54 +12,95 @@ def get_file_size(file_path : str) -> int:
 	return 0
 
 
-def same_file_extension(file_paths : List[str]) -> bool:
-	file_extensions : List[str] = []
+def get_file_name(file_path : str) -> Optional[str]:
+	file_name, _ = os.path.splitext(os.path.basename(file_path))
 
-	for file_path in file_paths:
-		_, file_extension = os.path.splitext(file_path.lower())
+	if file_name:
+		return file_name
+	return None
 
-		if file_extensions and file_extension not in file_extensions:
-			return False
-		file_extensions.append(file_extension)
-	return True
+
+def get_file_extension(file_path : str) -> Optional[str]:
+	_, file_extension = os.path.splitext(file_path)
+
+	if file_extension:
+		return file_extension.lower()
+	return None
+
+
+def get_file_format(file_path : str) -> Optional[str]:
+	file_extension = get_file_extension(file_path)
+
+	if file_extension:
+		if file_extension == '.jpg':
+			return 'jpeg'
+		if file_extension == '.tif':
+			return 'tiff'
+		return file_extension.lstrip('.')
+	return None
+
+
+def same_file_extension(first_file_path : str, second_file_path : str) -> bool:
+	first_file_extension = get_file_extension(first_file_path)
+	second_file_extension = get_file_extension(second_file_path)
+
+	if first_file_extension and second_file_extension:
+		return get_file_extension(first_file_path) == get_file_extension(second_file_path)
+	return False
 
 
 def is_file(file_path : str) -> bool:
-	return bool(file_path and os.path.isfile(file_path))
-
-
-def is_directory(directory_path : str) -> bool:
-	return bool(directory_path and os.path.isdir(directory_path))
-
-
-def in_directory(file_path : str) -> bool:
-	if file_path and not is_directory(file_path):
-		return is_directory(os.path.dirname(file_path))
+	if file_path:
+		return os.path.isfile(file_path)
 	return False
 
 
 def is_audio(audio_path : str) -> bool:
-	return is_file(audio_path) and filetype.helpers.is_audio(audio_path)
+	return is_file(audio_path) and get_file_format(audio_path) in facefusion.choices.audio_formats
 
 
 def has_audio(audio_paths : List[str]) -> bool:
 	if audio_paths:
-		return any(is_audio(audio_path) for audio_path in audio_paths)
+		return any(map(is_audio, audio_paths))
+	return False
+
+
+def are_audios(audio_paths : List[str]) -> bool:
+	if audio_paths:
+		return all(map(is_audio, audio_paths))
 	return False
 
 
 def is_image(image_path : str) -> bool:
-	return is_file(image_path) and filetype.helpers.is_image(image_path)
+	return is_file(image_path) and get_file_format(image_path) in facefusion.choices.image_formats
 
 
-def has_image(image_paths: List[str]) -> bool:
+def has_image(image_paths : List[str]) -> bool:
 	if image_paths:
 		return any(is_image(image_path) for image_path in image_paths)
 	return False
 
 
+def are_images(image_paths : List[str]) -> bool:
+	if image_paths:
+		return all(map(is_image, image_paths))
+	return False
+
+
 def is_video(video_path : str) -> bool:
-	return is_file(video_path) and filetype.helpers.is_video(video_path)
+	return is_file(video_path) and get_file_format(video_path) in facefusion.choices.video_formats
+
+
+def has_video(video_paths : List[str]) -> bool:
+	if video_paths:
+		return any(map(is_video, video_paths))
+	return False
+
+
+def are_videos(video_paths : List[str]) -> bool:
+	if video_paths:
+		return any(map(is_video, video_paths))
+	return False
 
 
 def filter_audio_paths(paths : List[str]) -> List[str]:
@@ -79,24 +115,6 @@ def filter_image_paths(paths : List[str]) -> List[str]:
 	return []
 
 
-def resolve_relative_path(path : str) -> str:
-	return os.path.abspath(os.path.join(os.path.dirname(__file__), path))
-
-
-def sanitize_path_for_windows(full_path : str) -> Optional[str]:
-	buffer_size = 0
-
-	while True:
-		unicode_buffer = ctypes.create_unicode_buffer(buffer_size)
-		buffer_limit = ctypes.windll.kernel32.GetShortPathNameW(full_path, unicode_buffer, buffer_size) #type:ignore[attr-defined]
-
-		if buffer_size > buffer_limit:
-			return unicode_buffer.value
-		if buffer_limit == 0:
-			return None
-		buffer_size = buffer_limit
-
-
 def copy_file(file_path : str, move_path : str) -> bool:
 	if is_file(file_path):
 		shutil.copy(file_path, move_path)
@@ -118,19 +136,45 @@ def remove_file(file_path : str) -> bool:
 	return False
 
 
-def create_directory(directory_path : str) -> bool:
-	if directory_path and not is_file(directory_path):
-		Path(directory_path).mkdir(parents = True, exist_ok = True)
-		return is_directory(directory_path)
+def resolve_file_paths(directory_path : str) -> List[str]:
+	file_paths : List[str] = []
+
+	if is_directory(directory_path):
+		file_names_and_extensions = sorted(os.listdir(directory_path))
+
+		for file_name_and_extension in file_names_and_extensions:
+			if not file_name_and_extension.startswith(('.', '__')):
+				file_path = os.path.join(directory_path, file_name_and_extension)
+				file_paths.append(file_path)
+
+	return file_paths
+
+
+def resolve_file_pattern(file_pattern : str) -> List[str]:
+	if in_directory(file_pattern):
+		return sorted(glob.glob(file_pattern))
+	return []
+
+
+def is_directory(directory_path : str) -> bool:
+	if directory_path:
+		return os.path.isdir(directory_path)
 	return False
 
 
-def list_directory(directory_path : str) -> Optional[List[str]]:
-	if is_directory(directory_path):
-		files = os.listdir(directory_path)
-		files = [ Path(file).stem for file in files if not Path(file).stem.startswith(('.', '__')) ]
-		return sorted(files)
-	return None
+def in_directory(file_path : str) -> bool:
+	if file_path:
+		directory_path = os.path.dirname(file_path)
+		if directory_path:
+			return not is_directory(file_path) and is_directory(directory_path)
+	return False
+
+
+def create_directory(directory_path : str) -> bool:
+	if directory_path and not is_file(directory_path):
+		os.makedirs(directory_path, exist_ok = True)
+		return is_directory(directory_path)
+	return False
 
 
 def remove_directory(directory_path : str) -> bool:
@@ -138,3 +182,7 @@ def remove_directory(directory_path : str) -> bool:
 		shutil.rmtree(directory_path, ignore_errors = True)
 		return not is_directory(directory_path)
 	return False
+
+
+def resolve_relative_path(path : str) -> str:
+	return os.path.abspath(os.path.join(os.path.dirname(__file__), path))

facefusion/hash_helper.py

@@ -2,7 +2,7 @@ import os
 import zlib
 from typing import Optional
 
-from facefusion.filesystem import is_file
+from facefusion.filesystem import get_file_name, is_file
 
 
 def create_hash(content : bytes) -> str:
@@ -13,8 +13,8 @@ def validate_hash(validate_path : str) -> bool:
 	hash_path = get_hash_path(validate_path)
 
 	if is_file(hash_path):
-		with open(hash_path, 'r') as hash_file:
-			hash_content = hash_file.read().strip()
+		with open(hash_path) as hash_file:
+			hash_content = hash_file.read()
 
 		with open(validate_path, 'rb') as validate_file:
 			validate_content = validate_file.read()
@@ -25,8 +25,8 @@ def validate_hash(validate_path : str) -> bool:
 
 def get_hash_path(validate_path : str) -> Optional[str]:
 	if is_file(validate_path):
-		validate_directory_path, _ = os.path.split(validate_path)
-		validate_file_name, _ = os.path.splitext(_)
+		validate_directory_path, file_name_and_extension = os.path.split(validate_path)
+		validate_file_name = get_file_name(file_name_and_extension)
 
 		return os.path.join(validate_directory_path, validate_file_name + '.hash')
 	return None

facefusion/inference_manager.py

@@ -1,79 +1,74 @@
-from functools import lru_cache
+import importlib
 from time import sleep
 from typing import List
 
-import onnx
 from onnxruntime import InferenceSession
 
 from facefusion import process_manager, state_manager
 from facefusion.app_context import detect_app_context
-from facefusion.execution import create_execution_providers, has_execution_provider
-from facefusion.thread_helper import thread_lock
-from facefusion.typing import DownloadSet, ExecutionProviderKey, InferencePool, InferencePoolSet, ModelInitializer
+from facefusion.execution import create_inference_session_providers
+from facefusion.filesystem import is_file
+from facefusion.types import DownloadSet, ExecutionProvider, InferencePool, InferencePoolSet
 
-INFERENCE_POOLS : InferencePoolSet =\
+INFERENCE_POOL_SET : InferencePoolSet =\
 {
-	'cli': {}, # type:ignore[typeddict-item]
-	'ui': {} # type:ignore[typeddict-item]
+	'cli': {},
+	'ui': {}
 }
 
 
-def get_inference_pool(model_context : str, model_sources : DownloadSet) -> InferencePool:
-	global INFERENCE_POOLS
+def get_inference_pool(module_name : str, model_names : List[str], model_source_set : DownloadSet) -> InferencePool:
+	while process_manager.is_checking():
+		sleep(0.5)
+	execution_device_id = state_manager.get_item('execution_device_id')
+	execution_providers = resolve_execution_providers(module_name)
+	app_context = detect_app_context()
+	inference_context = get_inference_context(module_name, model_names, execution_device_id, execution_providers)
 
-	with thread_lock():
-		while process_manager.is_checking():
-			sleep(0.5)
-		app_context = detect_app_context()
-		inference_context = get_inference_context(model_context)
+	if app_context == 'cli' and INFERENCE_POOL_SET.get('ui').get(inference_context):
+		INFERENCE_POOL_SET['cli'][inference_context] = INFERENCE_POOL_SET.get('ui').get(inference_context)
+	if app_context == 'ui' and INFERENCE_POOL_SET.get('cli').get(inference_context):
+		INFERENCE_POOL_SET['ui'][inference_context] = INFERENCE_POOL_SET.get('cli').get(inference_context)
+	if not INFERENCE_POOL_SET.get(app_context).get(inference_context):
+		INFERENCE_POOL_SET[app_context][inference_context] = create_inference_pool(model_source_set, execution_device_id, execution_providers)
 
-		if app_context == 'cli' and INFERENCE_POOLS.get('ui').get(inference_context):
-			INFERENCE_POOLS['cli'][inference_context] = INFERENCE_POOLS.get('ui').get(inference_context)
-		if app_context == 'ui' and INFERENCE_POOLS.get('cli').get(inference_context):
-			INFERENCE_POOLS['ui'][inference_context] = INFERENCE_POOLS.get('cli').get(inference_context)
-		if not INFERENCE_POOLS.get(app_context).get(inference_context):
-			execution_provider_keys = resolve_execution_provider_keys(model_context)
-			INFERENCE_POOLS[app_context][inference_context] = create_inference_pool(model_sources, state_manager.get_item('execution_device_id'), execution_provider_keys)
-
-		return INFERENCE_POOLS.get(app_context).get(inference_context)
+	return INFERENCE_POOL_SET.get(app_context).get(inference_context)
 
 
-def create_inference_pool(model_sources : DownloadSet, execution_device_id : str, execution_provider_keys : List[ExecutionProviderKey]) -> InferencePool:
+def create_inference_pool(model_source_set : DownloadSet, execution_device_id : str, execution_providers : List[ExecutionProvider]) -> InferencePool:
 	inference_pool : InferencePool = {}
 
-	for model_name in model_sources.keys():
-		inference_pool[model_name] = create_inference_session(model_sources.get(model_name).get('path'), execution_device_id, execution_provider_keys)
+	for model_name in model_source_set.keys():
+		model_path = model_source_set.get(model_name).get('path')
+		if is_file(model_path):
+			inference_pool[model_name] = create_inference_session(model_path, execution_device_id, execution_providers)
+
 	return inference_pool
 
 
-def clear_inference_pool(model_context : str) -> None:
-	global INFERENCE_POOLS
-
+def clear_inference_pool(module_name : str, model_names : List[str]) -> None:
+	execution_device_id = state_manager.get_item('execution_device_id')
+	execution_providers = resolve_execution_providers(module_name)
 	app_context = detect_app_context()
-	inference_context = get_inference_context(model_context)
+	inference_context = get_inference_context(module_name, model_names, execution_device_id, execution_providers)
 
-	if INFERENCE_POOLS.get(app_context).get(inference_context):
-		del INFERENCE_POOLS[app_context][inference_context]
+	if INFERENCE_POOL_SET.get(app_context).get(inference_context):
+		del INFERENCE_POOL_SET[app_context][inference_context]
 
 
-def create_inference_session(model_path : str, execution_device_id : str, execution_provider_keys : List[ExecutionProviderKey]) -> InferenceSession:
-	execution_providers = create_execution_providers(execution_device_id, execution_provider_keys)
-	return InferenceSession(model_path, providers = execution_providers)
+def create_inference_session(model_path : str, execution_device_id : str, execution_providers : List[ExecutionProvider]) -> InferenceSession:
+	inference_session_providers = create_inference_session_providers(execution_device_id, execution_providers)
+	return InferenceSession(model_path, providers = inference_session_providers)
 
 
-@lru_cache(maxsize = None)
-def get_static_model_initializer(model_path : str) -> ModelInitializer:
-	model = onnx.load(model_path)
-	return onnx.numpy_helper.to_array(model.graph.initializer[-1])
-
-
-def resolve_execution_provider_keys(model_context : str) -> List[ExecutionProviderKey]:
-	if has_execution_provider('coreml') and (model_context.startswith('facefusion.processors.modules.age_modifier') or model_context.startswith('facefusion.processors.modules.frame_colorizer')):
-		return [ 'cpu' ]
-	return state_manager.get_item('execution_providers')
-
-
-def get_inference_context(model_context : str) -> str:
-	execution_provider_keys = resolve_execution_provider_keys(model_context)
-	inference_context = model_context + '.' + '_'.join(execution_provider_keys)
+def get_inference_context(module_name : str, model_names : List[str], execution_device_id : str, execution_providers : List[ExecutionProvider]) -> str:
+	inference_context = '.'.join([ module_name ] + model_names + [ execution_device_id ] + list(execution_providers))
 	return inference_context
+
+
+def resolve_execution_providers(module_name : str) -> List[ExecutionProvider]:
+	module = importlib.import_module(module_name)
+
+	if hasattr(module, 'resolve_execution_providers'):
+		return getattr(module, 'resolve_execution_providers')()
+	return state_manager.get_item('execution_providers')

facefusion/installer.py

@@ -3,60 +3,63 @@ import shutil
 import signal
 import subprocess
 import sys
-import tempfile
 from argparse import ArgumentParser, HelpFormatter
-from typing import Dict, Tuple
+from functools import partial
+from types import FrameType
 
 from facefusion import metadata, wording
-from facefusion.common_helper import is_linux, is_macos, is_windows
+from facefusion.common_helper import is_linux, is_windows
 
-ONNXRUNTIMES : Dict[str, Tuple[str, str]] = {}
-
-if is_macos():
-	ONNXRUNTIMES['default'] = ('onnxruntime', '1.19.2')
-else:
-	ONNXRUNTIMES['default'] = ('onnxruntime', '1.19.2')
-	ONNXRUNTIMES['cuda'] = ('onnxruntime-gpu', '1.19.2')
-	ONNXRUNTIMES['openvino'] = ('onnxruntime-openvino', '1.19.0')
-if is_linux():
-	ONNXRUNTIMES['rocm'] = ('onnxruntime-rocm', '1.18.0')
+ONNXRUNTIME_SET =\
+{
+	'default': ('onnxruntime', '1.22.0')
+}
+if is_windows() or is_linux():
+	ONNXRUNTIME_SET['cuda'] = ('onnxruntime-gpu', '1.22.0')
+	ONNXRUNTIME_SET['openvino'] = ('onnxruntime-openvino', '1.22.0')
 if is_windows():
-	ONNXRUNTIMES['directml'] = ('onnxruntime-directml', '1.17.3')
+	ONNXRUNTIME_SET['directml'] = ('onnxruntime-directml', '1.17.3')
+if is_linux():
+	ONNXRUNTIME_SET['rocm'] = ('onnxruntime-rocm', '1.21.0')
 
 
 def cli() -> None:
-	signal.signal(signal.SIGINT, lambda signal_number, frame: sys.exit(0))
-	program = ArgumentParser(formatter_class = lambda prog: HelpFormatter(prog, max_help_position = 50))
-	program.add_argument('--onnxruntime', help = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIMES.keys(), required = True)
+	signal.signal(signal.SIGINT, signal_exit)
+	program = ArgumentParser(formatter_class = partial(HelpFormatter, max_help_position = 50))
+	program.add_argument('--onnxruntime', help = wording.get('help.install_dependency').format(dependency = 'onnxruntime'), choices = ONNXRUNTIME_SET.keys(), required = True)
 	program.add_argument('--skip-conda', help = wording.get('help.skip_conda'), action = 'store_true')
 	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
 	run(program)
 
 
+def signal_exit(signum : int, frame : FrameType) -> None:
+	sys.exit(0)
+
+
 def run(program : ArgumentParser) -> None:
 	args = program.parse_args()
 	has_conda = 'CONDA_PREFIX' in os.environ
-	onnxruntime_name, onnxruntime_version = ONNXRUNTIMES.get(args.onnxruntime)
+	onnxruntime_name, onnxruntime_version = ONNXRUNTIME_SET.get(args.onnxruntime)
 
 	if not args.skip_conda and not has_conda:
 		sys.stdout.write(wording.get('conda_not_activated') + os.linesep)
 		sys.exit(1)
 
-	subprocess.call([ shutil.which('pip'), 'install', '-r', 'requirements.txt', '--force-reinstall' ])
+	with open('requirements.txt') as file:
+
+		for line in file.readlines():
+			__line__ = line.strip()
+			if not __line__.startswith('onnxruntime'):
+				subprocess.call([ shutil.which('pip'), 'install', line, '--force-reinstall' ])
 
 	if args.onnxruntime == 'rocm':
 		python_id = 'cp' + str(sys.version_info.major) + str(sys.version_info.minor)
 
-		if python_id == 'cp310':
-			wheel_name = 'onnxruntime_rocm-' + onnxruntime_version +'-' + python_id + '-' + python_id + '-linux_x86_64.whl'
-			wheel_path = os.path.join(tempfile.gettempdir(), wheel_name)
-			wheel_url = 'https://repo.radeon.com/rocm/manylinux/rocm-rel-6.2/' + wheel_name
-			subprocess.call([ shutil.which('curl'), '--silent', '--location', '--continue-at', '-', '--output', wheel_path, wheel_url ])
-			subprocess.call([ shutil.which('pip'), 'uninstall', 'onnxruntime', wheel_path, '-y', '-q' ])
-			subprocess.call([ shutil.which('pip'), 'install', wheel_path, '--force-reinstall' ])
-			os.remove(wheel_path)
+		if python_id in [ 'cp310', 'cp312' ]:
+			wheel_name = 'onnxruntime_rocm-' + onnxruntime_version + '-' + python_id + '-' + python_id + '-linux_x86_64.whl'
+			wheel_url = 'https://repo.radeon.com/rocm/manylinux/rocm-rel-6.4/' + wheel_name
+			subprocess.call([ shutil.which('pip'), 'install', wheel_url, '--force-reinstall' ])
 	else:
-		subprocess.call([ shutil.which('pip'), 'uninstall', 'onnxruntime', onnxruntime_name, '-y', '-q' ])
 		subprocess.call([ shutil.which('pip'), 'install', onnxruntime_name + '==' + onnxruntime_version, '--force-reinstall' ])
 
 	if args.onnxruntime == 'cuda' and has_conda:
@@ -72,7 +75,7 @@ def run(program : ArgumentParser) -> None:
 				os.path.join(os.getenv('CONDA_PREFIX'), 'lib'),
 				os.path.join(os.getenv('CONDA_PREFIX'), 'lib', python_id, 'site-packages', 'tensorrt_libs')
 			])
-			library_paths = [ library_path for library_path in library_paths if os.path.exists(library_path) ]
+			library_paths = list(dict.fromkeys([ library_path for library_path in library_paths if os.path.exists(library_path) ]))
 
 			subprocess.call([ shutil.which('conda'), 'env', 'config', 'vars', 'set', 'LD_LIBRARY_PATH=' + os.pathsep.join(library_paths) ])
 
@@ -85,9 +88,9 @@ def run(program : ArgumentParser) -> None:
 				os.path.join(os.getenv('CONDA_PREFIX'), 'Lib'),
 				os.path.join(os.getenv('CONDA_PREFIX'), 'Lib', 'site-packages', 'tensorrt_libs')
 			])
-			library_paths = [ library_path for library_path in library_paths if os.path.exists(library_path) ]
+			library_paths = list(dict.fromkeys([ library_path for library_path in library_paths if os.path.exists(library_path) ]))
 
 			subprocess.call([ shutil.which('conda'), 'env', 'config', 'vars', 'set', 'PATH=' + os.pathsep.join(library_paths) ])
 
-	if onnxruntime_version < '1.19.0':
+	if args.onnxruntime == 'directml':
 		subprocess.call([ shutil.which('pip'), 'install', 'numpy==1.26.4', '--force-reinstall' ])

facefusion/jobs/job_helper.py

@@ -2,11 +2,14 @@ import os
 from datetime import datetime
 from typing import Optional
 
+from facefusion.filesystem import get_file_extension, get_file_name
+
 
 def get_step_output_path(job_id : str, step_index : int, output_path : str) -> Optional[str]:
 	if output_path:
 		output_directory_path, _ = os.path.split(output_path)
-		output_file_name, output_file_extension = os.path.splitext(_)
+		output_file_name = get_file_name(_)
+		output_file_extension = get_file_extension(_)
 		return os.path.join(output_directory_path, output_file_name + '-' + job_id + '-' + str(step_index) + output_file_extension)
 	return None
 

facefusion/jobs/job_list.py

@@ -3,7 +3,7 @@ from typing import Optional, Tuple
 
 from facefusion.date_helper import describe_time_ago
 from facefusion.jobs import job_manager
-from facefusion.typing import JobStatus, TableContents, TableHeaders
+from facefusion.types import JobStatus, TableContents, TableHeaders
 
 
 def compose_job_list(job_status : JobStatus) -> Tuple[TableHeaders, TableContents]:

facefusion/jobs/job_manager.py

@@ -1,15 +1,13 @@
-import glob
 import os
 from copy import copy
 from typing import List, Optional
 
-from facefusion.choices import job_statuses
+import facefusion.choices
 from facefusion.date_helper import get_current_date_time
-from facefusion.filesystem import create_directory, is_directory, is_file, move_file, remove_directory, remove_file
+from facefusion.filesystem import create_directory, get_file_name, is_directory, is_file, move_file, remove_directory, remove_file, resolve_file_pattern
 from facefusion.jobs.job_helper import get_step_output_path
 from facefusion.json import read_json, write_json
-from facefusion.temp_helper import create_base_directory
-from facefusion.typing import Args, Job, JobSet, JobStatus, JobStep, JobStepStatus
+from facefusion.types import Args, Job, JobSet, JobStatus, JobStep, JobStepStatus
 
 JOBS_PATH : Optional[str] = None
 
@@ -18,9 +16,8 @@ def init_jobs(jobs_path : str) -> bool:
 	global JOBS_PATH
 
 	JOBS_PATH = jobs_path
-	job_status_paths = [ os.path.join(JOBS_PATH, job_status) for job_status in job_statuses ]
+	job_status_paths = [ os.path.join(JOBS_PATH, job_status) for job_status in facefusion.choices.job_statuses ]
 
-	create_base_directory()
 	for job_status_path in job_status_paths:
 		create_directory(job_status_path)
 	return all(is_directory(status_path) for status_path in job_status_paths)
@@ -51,14 +48,17 @@ def submit_job(job_id : str) -> bool:
 	return False
 
 
-def submit_jobs() -> bool:
+def submit_jobs(halt_on_error : bool) -> bool:
 	drafted_job_ids = find_job_ids('drafted')
+	has_error = False
 
 	if drafted_job_ids:
 		for job_id in drafted_job_ids:
 			if not submit_job(job_id):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
@@ -66,34 +66,37 @@ def delete_job(job_id : str) -> bool:
 	return delete_job_file(job_id)
 
 
-def delete_jobs() -> bool:
+def delete_jobs(halt_on_error : bool) -> bool:
 	job_ids = find_job_ids('drafted') + find_job_ids('queued') + find_job_ids('failed') + find_job_ids('completed')
+	has_error = False
 
 	if job_ids:
 		for job_id in job_ids:
 			if not delete_job(job_id):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
 def find_jobs(job_status : JobStatus) -> JobSet:
 	job_ids = find_job_ids(job_status)
-	jobs : JobSet = {}
+	job_set : JobSet = {}
 
 	for job_id in job_ids:
-		jobs[job_id] = read_job_file(job_id)
-	return jobs
+		job_set[job_id] = read_job_file(job_id)
+	return job_set
 
 
 def find_job_ids(job_status : JobStatus) -> List[str]:
 	job_pattern = os.path.join(JOBS_PATH, job_status, '*.json')
-	job_files = glob.glob(job_pattern)
-	job_files.sort(key = os.path.getmtime)
+	job_paths = resolve_file_pattern(job_pattern)
+	job_paths.sort(key = os.path.getmtime)
 	job_ids = []
 
-	for job_file in job_files:
-		job_id, _ = os.path.splitext(os.path.basename(job_file))
+	for job_path in job_paths:
+		job_id = get_file_name(job_path)
 		job_ids.append(job_id)
 	return job_ids
 
@@ -185,7 +188,6 @@ def set_step_status(job_id : str, step_index : int, step_status : JobStepStatus)
 
 	if job:
 		steps = job.get('steps')
-
 		if has_step(job_id, step_index):
 			steps[step_index]['status'] = step_status
 			return update_job_file(job_id, job)
@@ -248,9 +250,9 @@ def find_job_path(job_id : str) -> Optional[str]:
 	job_file_name = get_job_file_name(job_id)
 
 	if job_file_name:
-		for job_status in job_statuses:
+		for job_status in facefusion.choices.job_statuses:
 			job_pattern = os.path.join(JOBS_PATH, job_status, job_file_name)
-			job_paths = glob.glob(job_pattern)
+			job_paths = resolve_file_pattern(job_pattern)
 
 			for job_path in job_paths:
 				return job_path

facefusion/jobs/job_runner.py

@@ -1,7 +1,7 @@
 from facefusion.ffmpeg import concat_video
-from facefusion.filesystem import is_image, is_video, move_file, remove_file
+from facefusion.filesystem import are_images, are_videos, move_file, remove_file
 from facefusion.jobs import job_helper, job_manager
-from facefusion.typing import JobOutputSet, JobStep, ProcessStep
+from facefusion.types import JobOutputSet, JobStep, ProcessStep
 
 
 def run_job(job_id : str, process_step : ProcessStep) -> bool:
@@ -16,14 +16,17 @@ def run_job(job_id : str, process_step : ProcessStep) -> bool:
 	return False
 
 
-def run_jobs(process_step : ProcessStep) -> bool:
+def run_jobs(process_step : ProcessStep, halt_on_error : bool) -> bool:
 	queued_job_ids = job_manager.find_job_ids('queued')
+	has_error = False
 
 	if queued_job_ids:
 		for job_id in queued_job_ids:
 			if not run_job(job_id, process_step):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
@@ -35,14 +38,17 @@ def retry_job(job_id : str, process_step : ProcessStep) -> bool:
 	return False
 
 
-def retry_jobs(process_step : ProcessStep) -> bool:
+def retry_jobs(process_step : ProcessStep, halt_on_error : bool) -> bool:
 	failed_job_ids = job_manager.find_job_ids('failed')
+	has_error = False
 
 	if failed_job_ids:
 		for job_id in failed_job_ids:
 			if not retry_job(job_id, process_step):
-				return False
-		return True
+				has_error = True
+				if halt_on_error:
+					return False
+		return not has_error
 	return False
 
 
@@ -73,10 +79,10 @@ def finalize_steps(job_id : str) -> bool:
 	output_set = collect_output_set(job_id)
 
 	for output_path, temp_output_paths in output_set.items():
-		if all(map(is_video, temp_output_paths)):
+		if are_videos(temp_output_paths):
 			if not concat_video(output_path, temp_output_paths):
 				return False
-		if any(map(is_image, temp_output_paths)):
+		if are_images(temp_output_paths):
 			for temp_output_path in temp_output_paths:
 				if not move_file(temp_output_path, output_path):
 					return False
@@ -95,12 +101,12 @@ def clean_steps(job_id: str) -> bool:
 
 def collect_output_set(job_id : str) -> JobOutputSet:
 	steps = job_manager.get_steps(job_id)
-	output_set : JobOutputSet = {}
+	job_output_set : JobOutputSet = {}
 
 	for index, step in enumerate(steps):
 		output_path = step.get('args').get('output_path')
 
 		if output_path:
 			step_output_path = job_manager.get_step_output_path(job_id, index, output_path)
-			output_set.setdefault(output_path, []).append(step_output_path)
-	return output_set
+			job_output_set.setdefault(output_path, []).append(step_output_path)
+	return job_output_set

facefusion/jobs/job_store.py

@@ -1,6 +1,6 @@
 from typing import List
 
-from facefusion.typing import JobStore
+from facefusion.types import JobStore
 
 JOB_STORE : JobStore =\
 {

facefusion/json.py

@@ -3,13 +3,13 @@ from json import JSONDecodeError
 from typing import Optional
 
 from facefusion.filesystem import is_file
-from facefusion.typing import Content
+from facefusion.types import Content
 
 
 def read_json(json_path : str) -> Optional[Content]:
 	if is_file(json_path):
 		try:
-			with open(json_path, 'r') as json_file:
+			with open(json_path) as json_file:
 				return json.load(json_file)
 		except JSONDecodeError:
 			pass

facefusion/logger.py

@@ -1,14 +1,13 @@
 from logging import Logger, basicConfig, getLogger
-from typing import Tuple
 
-from facefusion.choices import log_level_set
+import facefusion.choices
 from facefusion.common_helper import get_first, get_last
-from facefusion.typing import LogLevel, TableContents, TableHeaders
+from facefusion.types import LogLevel
 
 
 def init(log_level : LogLevel) -> None:
 	basicConfig(format = '%(message)s')
-	get_package_logger().setLevel(log_level_set.get(log_level))
+	get_package_logger().setLevel(facefusion.choices.log_level_set.get(log_level))
 
 
 def get_package_logger() -> Logger:
@@ -32,46 +31,15 @@ def error(message : str, module_name : str) -> None:
 
 
 def create_message(message : str, module_name : str) -> str:
-	scopes = module_name.split('.')
-	first_scope = get_first(scopes)
-	last_scope = get_last(scopes)
+	module_names = module_name.split('.')
+	first_module_name = get_first(module_names)
+	last_module_name = get_last(module_names)
 
-	if first_scope and last_scope:
-		return '[' + first_scope.upper() + '.' + last_scope.upper() + '] ' + message
+	if first_module_name and last_module_name:
+		return '[' + first_module_name.upper() + '.' + last_module_name.upper() + '] ' + message
 	return message
 
 
-def table(headers : TableHeaders, contents : TableContents) -> None:
-	package_logger = get_package_logger()
-	table_column, table_separator = create_table_parts(headers, contents)
-
-	package_logger.info(table_separator)
-	package_logger.info(table_column.format(*headers))
-	package_logger.info(table_separator)
-
-	for content in contents:
-		content = [ value if value else '' for value in content ]
-		package_logger.info(table_column.format(*content))
-
-	package_logger.info(table_separator)
-
-
-def create_table_parts(headers : TableHeaders, contents : TableContents) -> Tuple[str, str]:
-	column_parts = []
-	separator_parts = []
-	widths = [ len(header) for header in headers ]
-
-	for content in contents:
-		for index, value in enumerate(content):
-			widths[index] = max(widths[index], len(str(value)))
-
-	for width in widths:
-		column_parts.append('{:<' + str(width) + '}')
-		separator_parts.append('-' * width)
-
-	return '| ' + ' | '.join(column_parts) + ' |', '+-' + '-+-'.join(separator_parts) + '-+'
-
-
 def enable() -> None:
 	get_package_logger().disabled = False
 

facefusion/metadata.py

@@ -4,8 +4,8 @@ METADATA =\
 {
 	'name': 'FaceFusion',
 	'description': 'Industry leading face manipulation platform',
-	'version': '3.0.0',
-	'license': 'MIT',
+	'version': '3.3.1',
+	'license': 'OpenRAIL-AS',
 	'author': 'Henry Ruhs',
 	'url': 'https://facefusion.io'
 }

facefusion/model_helper.py

@@ -0,0 +1,11 @@
+from functools import lru_cache
+
+import onnx
+
+from facefusion.types import ModelInitializer
+
+
+@lru_cache(maxsize = None)
+def get_static_model_initializer(model_path : str) -> ModelInitializer:
+	model = onnx.load(model_path)
+	return onnx.numpy_helper.to_array(model.graph.initializer[-1])

facefusion/normalizer.py

@@ -1,6 +1,6 @@
 from typing import List, Optional
 
-from facefusion.typing import Fps, Padding
+from facefusion.types import Fps, Padding
 
 
 def normalize_padding(padding : Optional[List[int]]) -> Optional[Padding]:

facefusion/process_manager.py

@@ -1,6 +1,6 @@
 from typing import Generator, List
 
-from facefusion.typing import ProcessState, QueuePayload
+from facefusion.types import ProcessState, QueuePayload
 
 PROCESS_STATE : ProcessState = 'pending'
 

facefusion/processors/choices.py

@@ -1,9 +1,179 @@
 from typing import List, Sequence
 
 from facefusion.common_helper import create_float_range, create_int_range
-from facefusion.processors.typing import AgeModifierModel, ExpressionRestorerModel, FaceDebuggerItem, FaceEditorModel, FaceEnhancerModel, FaceSwapperSet, FrameColorizerModel, FrameEnhancerModel, LipSyncerModel
+from facefusion.filesystem import get_file_name, resolve_file_paths, resolve_relative_path
+from facefusion.processors.types import AgeModifierModel, DeepSwapperModel, ExpressionRestorerModel, FaceDebuggerItem, FaceEditorModel, FaceEnhancerModel, FaceSwapperModel, FaceSwapperSet, FrameColorizerModel, FrameEnhancerModel, LipSyncerModel
 
 age_modifier_models : List[AgeModifierModel] = [ 'styleganex_age' ]
+deep_swapper_models : List[DeepSwapperModel] =\
+[
+	'druuzil/adam_levine_320',
+	'druuzil/adrianne_palicki_384',
+	'druuzil/agnetha_falskog_224',
+	'druuzil/alan_ritchson_320',
+	'druuzil/alicia_vikander_320',
+	'druuzil/amber_midthunder_320',
+	'druuzil/andras_arato_384',
+	'druuzil/andrew_tate_320',
+	'druuzil/angelina_jolie_384',
+	'druuzil/anne_hathaway_320',
+	'druuzil/anya_chalotra_320',
+	'druuzil/arnold_schwarzenegger_320',
+	'druuzil/benjamin_affleck_320',
+	'druuzil/benjamin_stiller_384',
+	'druuzil/bradley_pitt_224',
+	'druuzil/brie_larson_384',
+	'druuzil/bruce_campbell_384',
+	'druuzil/bryan_cranston_320',
+	'druuzil/catherine_blanchett_352',
+	'druuzil/christian_bale_320',
+	'druuzil/christopher_hemsworth_320',
+	'druuzil/christoph_waltz_384',
+	'druuzil/cillian_murphy_320',
+	'druuzil/cobie_smulders_256',
+	'druuzil/dwayne_johnson_384',
+	'druuzil/edward_norton_320',
+	'druuzil/elisabeth_shue_320',
+	'druuzil/elizabeth_olsen_384',
+	'druuzil/elon_musk_320',
+	'druuzil/emily_blunt_320',
+	'druuzil/emma_stone_384',
+	'druuzil/emma_watson_320',
+	'druuzil/erin_moriarty_384',
+	'druuzil/eva_green_320',
+	'druuzil/ewan_mcgregor_320',
+	'druuzil/florence_pugh_320',
+	'druuzil/freya_allan_320',
+	'druuzil/gary_cole_224',
+	'druuzil/gigi_hadid_224',
+	'druuzil/harrison_ford_384',
+	'druuzil/hayden_christensen_320',
+	'druuzil/heath_ledger_320',
+	'druuzil/henry_cavill_448',
+	'druuzil/hugh_jackman_384',
+	'druuzil/idris_elba_320',
+	'druuzil/jack_nicholson_320',
+	'druuzil/james_carrey_384',
+	'druuzil/james_mcavoy_320',
+	'druuzil/james_varney_320',
+	'druuzil/jason_momoa_320',
+	'druuzil/jason_statham_320',
+	'druuzil/jennifer_connelly_384',
+	'druuzil/jimmy_donaldson_320',
+	'druuzil/jordan_peterson_384',
+	'druuzil/karl_urban_224',
+	'druuzil/kate_beckinsale_384',
+	'druuzil/laurence_fishburne_384',
+	'druuzil/lili_reinhart_320',
+	'druuzil/luke_evans_384',
+	'druuzil/mads_mikkelsen_384',
+	'druuzil/mary_winstead_320',
+	'druuzil/margaret_qualley_384',
+	'druuzil/melina_juergens_320',
+	'druuzil/michael_fassbender_320',
+	'druuzil/michael_fox_320',
+	'druuzil/millie_bobby_brown_320',
+	'druuzil/morgan_freeman_320',
+	'druuzil/patrick_stewart_224',
+	'druuzil/rachel_weisz_384',
+	'druuzil/rebecca_ferguson_320',
+	'druuzil/scarlett_johansson_320',
+	'druuzil/shannen_doherty_384',
+	'druuzil/seth_macfarlane_384',
+	'druuzil/thomas_cruise_320',
+	'druuzil/thomas_hanks_384',
+	'druuzil/william_murray_384',
+	'druuzil/zoe_saldana_384',
+	'edel/emma_roberts_224',
+	'edel/ivanka_trump_224',
+	'edel/lize_dzjabrailova_224',
+	'edel/sidney_sweeney_224',
+	'edel/winona_ryder_224',
+	'iperov/alexandra_daddario_224',
+	'iperov/alexei_navalny_224',
+	'iperov/amber_heard_224',
+	'iperov/dilraba_dilmurat_224',
+	'iperov/elon_musk_224',
+	'iperov/emilia_clarke_224',
+	'iperov/emma_watson_224',
+	'iperov/erin_moriarty_224',
+	'iperov/jackie_chan_224',
+	'iperov/james_carrey_224',
+	'iperov/jason_statham_320',
+	'iperov/keanu_reeves_320',
+	'iperov/margot_robbie_224',
+	'iperov/natalie_dormer_224',
+	'iperov/nicolas_coppola_224',
+	'iperov/robert_downey_224',
+	'iperov/rowan_atkinson_224',
+	'iperov/ryan_reynolds_224',
+	'iperov/scarlett_johansson_224',
+	'iperov/sylvester_stallone_224',
+	'iperov/thomas_cruise_224',
+	'iperov/thomas_holland_224',
+	'iperov/vin_diesel_224',
+	'iperov/vladimir_putin_224',
+	'jen/angelica_trae_288',
+	'jen/ella_freya_224',
+	'jen/emma_myers_320',
+	'jen/evie_pickerill_224',
+	'jen/kang_hyewon_320',
+	'jen/maddie_mead_224',
+	'jen/nicole_turnbull_288',
+	'mats/alica_schmidt_320',
+	'mats/ashley_alexiss_224',
+	'mats/billie_eilish_224',
+	'mats/brie_larson_224',
+	'mats/cara_delevingne_224',
+	'mats/carolin_kebekus_224',
+	'mats/chelsea_clinton_224',
+	'mats/claire_boucher_224',
+	'mats/corinna_kopf_224',
+	'mats/florence_pugh_224',
+	'mats/hillary_clinton_224',
+	'mats/jenna_fischer_224',
+	'mats/kim_jisoo_320',
+	'mats/mica_suarez_320',
+	'mats/shailene_woodley_224',
+	'mats/shraddha_kapoor_320',
+	'mats/yu_jimin_352',
+	'rumateus/alison_brie_224',
+	'rumateus/amber_heard_224',
+	'rumateus/angelina_jolie_224',
+	'rumateus/aubrey_plaza_224',
+	'rumateus/bridget_regan_224',
+	'rumateus/cobie_smulders_224',
+	'rumateus/deborah_woll_224',
+	'rumateus/dua_lipa_224',
+	'rumateus/emma_stone_224',
+	'rumateus/hailee_steinfeld_224',
+	'rumateus/hilary_duff_224',
+	'rumateus/jessica_alba_224',
+	'rumateus/jessica_biel_224',
+	'rumateus/john_cena_224',
+	'rumateus/kim_kardashian_224',
+	'rumateus/kristen_bell_224',
+	'rumateus/lucy_liu_224',
+	'rumateus/margot_robbie_224',
+	'rumateus/megan_fox_224',
+	'rumateus/meghan_markle_224',
+	'rumateus/millie_bobby_brown_224',
+	'rumateus/natalie_portman_224',
+	'rumateus/nicki_minaj_224',
+	'rumateus/olivia_wilde_224',
+	'rumateus/shay_mitchell_224',
+	'rumateus/sophie_turner_224',
+	'rumateus/taylor_swift_224'
+]
+
+custom_model_file_paths = resolve_file_paths(resolve_relative_path('../.assets/models/custom'))
+
+if custom_model_file_paths:
+
+	for model_file_path in custom_model_file_paths:
+		model_id = '/'.join([ 'custom', get_file_name(model_file_path) ])
+		deep_swapper_models.append(model_id)
+
 expression_restorer_models : List[ExpressionRestorerModel] = [ 'live_portrait' ]
 face_debugger_items : List[FaceDebuggerItem] = [ 'bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-landmark-68/5', 'face-mask', 'face-detector-score', 'face-landmarker-score', 'age', 'gender', 'race' ]
 face_editor_models : List[FaceEditorModel] = [ 'live_portrait' ]
@@ -14,18 +184,24 @@ face_swapper_set : FaceSwapperSet =\
 	'ghost_1_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
 	'ghost_2_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
 	'ghost_3_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
+	'hififace_unofficial_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
+	'hyperswap_1a_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
+	'hyperswap_1b_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
+	'hyperswap_1c_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
 	'inswapper_128': [ '128x128', '256x256', '384x384', '512x512', '768x768', '1024x1024' ],
 	'inswapper_128_fp16': [ '128x128', '256x256', '384x384', '512x512', '768x768', '1024x1024' ],
 	'simswap_256': [ '256x256', '512x512', '768x768', '1024x1024' ],
 	'simswap_unofficial_512': [ '512x512', '768x768', '1024x1024' ],
 	'uniface_256': [ '256x256', '512x512', '768x768', '1024x1024' ]
 }
+face_swapper_models : List[FaceSwapperModel] = list(face_swapper_set.keys())
 frame_colorizer_models : List[FrameColorizerModel] = [ 'ddcolor', 'ddcolor_artistic', 'deoldify', 'deoldify_artistic', 'deoldify_stable' ]
 frame_colorizer_sizes : List[str] = [ '192x192', '256x256', '384x384', '512x512' ]
-frame_enhancer_models : List[FrameEnhancerModel] = [ 'clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'span_kendata_x4', 'ultra_sharp_x4' ]
-lip_syncer_models : List[LipSyncerModel] = [ 'wav2lip_96', 'wav2lip_gan_96' ]
+frame_enhancer_models : List[FrameEnhancerModel] = [ 'clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'ultra_sharp_x4', 'ultra_sharp_2_x4' ]
+lip_syncer_models : List[LipSyncerModel] = [ 'edtalk_256', 'wav2lip_96', 'wav2lip_gan_96' ]
 
 age_modifier_direction_range : Sequence[int] = create_int_range(-100, 100, 1)
+deep_swapper_morph_range : Sequence[int] = create_int_range(0, 100, 1)
 expression_restorer_factor_range : Sequence[int] = create_int_range(0, 100, 1)
 face_editor_eyebrow_direction_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.05)
 face_editor_eye_gaze_horizontal_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.05)
@@ -42,5 +218,7 @@ face_editor_head_pitch_range : Sequence[float] = create_float_range(-1.0, 1.0, 0
 face_editor_head_yaw_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.05)
 face_editor_head_roll_range : Sequence[float] = create_float_range(-1.0, 1.0, 0.05)
 face_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
+face_enhancer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)
 frame_colorizer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
 frame_enhancer_blend_range : Sequence[int] = create_int_range(0, 100, 1)
+lip_syncer_weight_range : Sequence[float] = create_float_range(0.0, 1.0, 0.05)

facefusion/processors/core.py

@@ -9,7 +9,7 @@ from tqdm import tqdm
 
 from facefusion import logger, state_manager, wording
 from facefusion.exit_helper import hard_exit
-from facefusion.typing import ProcessFrames, QueuePayload
+from facefusion.types import ProcessFrames, QueuePayload
 
 PROCESSORS_METHODS =\
 [
@@ -53,21 +53,10 @@ def get_processors_modules(processors : List[str]) -> List[ModuleType]:
 	return processor_modules
 
 
-def clear_processors_modules(processors : List[str]) -> None:
-	for processor in processors:
-		processor_module = load_processor_module(processor)
-		processor_module.clear_inference_pool()
-
-
 def multi_process_frames(source_paths : List[str], temp_frame_paths : List[str], process_frames : ProcessFrames) -> None:
 	queue_payloads = create_queue_payloads(temp_frame_paths)
 	with tqdm(total = len(queue_payloads), desc = wording.get('processing'), unit = 'frame', ascii = ' =', disable = state_manager.get_item('log_level') in [ 'warn', 'error' ]) as progress:
-		progress.set_postfix(
-		{
-			'execution_providers': state_manager.get_item('execution_providers'),
-			'execution_thread_count': state_manager.get_item('execution_thread_count'),
-			'execution_queue_count': state_manager.get_item('execution_queue_count')
-		})
+		progress.set_postfix(execution_providers = state_manager.get_item('execution_providers'))
 		with ThreadPoolExecutor(max_workers = state_manager.get_item('execution_thread_count')) as executor:
 			futures = []
 			queue : Queue[QueuePayload] = create_queue(queue_payloads)

facefusion/processors/live_portrait.py

@@ -3,7 +3,7 @@ from typing import Tuple
 import numpy
 import scipy
 
-from facefusion.processors.typing import LivePortraitExpression, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitYaw
+from facefusion.processors.types import LivePortraitExpression, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitYaw
 
 EXPRESSION_MIN = numpy.array(
 [

facefusion/processors/modules/age_modifier.py

@@ -1,77 +1,90 @@
 from argparse import ArgumentParser
-from typing import Any, List
+from functools import lru_cache
+from typing import List
 
 import cv2
 import numpy
-from cv2.typing import Size
-from numpy.typing import NDArray
 
+import facefusion.choices
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, wording
 from facefusion.common_helper import create_int_metavar
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
+from facefusion.execution import has_execution_provider
 from facefusion.face_analyser import get_many_faces, get_one_face
 from facefusion.face_helper import merge_matrix, paste_back, scale_face_landmark_5, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_static_box_mask
+from facefusion.face_masker import create_box_mask, create_occlusion_mask
 from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
 from facefusion.face_store import get_reference_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import AgeModifierInputs
+from facefusion.processors.types import AgeModifierDirection, AgeModifierInputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, Face, InferencePool, Mask, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.vision import match_frame_color, read_image, read_static_image, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'styleganex_age':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'styleganex_age':
 		{
-			'age_modifier':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/styleganex_age.hash',
-				'path': resolve_relative_path('../.assets/models/styleganex_age.hash')
-			}
-		},
-		'sources':
-		{
-			'age_modifier':
+				'age_modifier':
+				{
+					'url': resolve_download_url('models-3.1.0', 'styleganex_age.hash'),
+					'path': resolve_relative_path('../.assets/models/styleganex_age.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/styleganex_age.onnx',
-				'path': resolve_relative_path('../.assets/models/styleganex_age.onnx')
+				'age_modifier':
+				{
+					'url': resolve_download_url('models-3.1.0', 'styleganex_age.onnx'),
+					'path': resolve_relative_path('../.assets/models/styleganex_age.onnx')
+				}
+			},
+			'templates':
+			{
+				'target': 'ffhq_512',
+				'target_with_background': 'styleganex_384'
+			},
+			'sizes':
+			{
+				'target': (256, 256),
+				'target_with_background': (384, 384)
 			}
-		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('age_modifier_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('age_modifier_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('age_modifier_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ state_manager.get_item('age_modifier_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	age_modifier_model = state_manager.get_item('age_modifier_model')
-	return MODEL_SET.get(age_modifier_model)
+	model_name = state_manager.get_item('age_modifier_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--age-modifier-model', help = wording.get('help.age_modifier_model'), default = config.get_str_value('processors.age_modifier_model', 'styleganex_age'), choices = processors_choices.age_modifier_models)
-		group_processors.add_argument('--age-modifier-direction', help = wording.get('help.age_modifier_direction'), type = int, default = config.get_int_value('processors.age_modifier_direction', '0'), choices = processors_choices.age_modifier_direction_range, metavar = create_int_metavar(processors_choices.age_modifier_direction_range))
+		group_processors.add_argument('--age-modifier-model', help = wording.get('help.age_modifier_model'), default = config.get_str_value('processors', 'age_modifier_model', 'styleganex_age'), choices = processors_choices.age_modifier_models)
+		group_processors.add_argument('--age-modifier-direction', help = wording.get('help.age_modifier_direction'), type = int, default = config.get_int_value('processors', 'age_modifier_direction', '0'), choices = processors_choices.age_modifier_direction_range, metavar = create_int_metavar(processors_choices.age_modifier_direction_range))
 		facefusion.jobs.job_store.register_step_keys([ 'age_modifier_model', 'age_modifier_direction' ])
 
 
@@ -81,11 +94,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -95,7 +107,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -103,6 +115,7 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -115,15 +128,14 @@ def post_process() -> None:
 
 
 def modify_age(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
-	model_template = get_model_options().get('template')
-	model_size = get_model_options().get('size')
-	crop_size = (model_size[0] // 2, model_size[1] // 2)
+	model_templates = get_model_options().get('templates')
+	model_sizes = get_model_options().get('sizes')
 	face_landmark_5 = target_face.landmark_set.get('5/68').copy()
-	extend_face_landmark_5 = scale_face_landmark_5(face_landmark_5, 2.0)
-	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_template, crop_size)
-	extend_vision_frame, extend_affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, extend_face_landmark_5, model_template, model_size)
+	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_templates.get('target'), model_sizes.get('target'))
+	extend_face_landmark_5 = scale_face_landmark_5(face_landmark_5, 0.875)
+	extend_vision_frame, extend_affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, extend_face_landmark_5, model_templates.get('target_with_background'), model_sizes.get('target_with_background'))
 	extend_vision_frame_raw = extend_vision_frame.copy()
-	box_mask = create_static_box_mask(model_size, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	box_mask = create_box_mask(extend_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_masks =\
 	[
 		box_mask
@@ -132,31 +144,36 @@ def modify_age(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFra
 	if 'occlusion' in state_manager.get_item('face_mask_types'):
 		occlusion_mask = create_occlusion_mask(crop_vision_frame)
 		combined_matrix = merge_matrix([ extend_affine_matrix, cv2.invertAffineTransform(affine_matrix) ])
-		occlusion_mask = cv2.warpAffine(occlusion_mask, combined_matrix, model_size)
+		occlusion_mask = cv2.warpAffine(occlusion_mask, combined_matrix, model_sizes.get('target_with_background'))
 		crop_masks.append(occlusion_mask)
 
 	crop_vision_frame = prepare_vision_frame(crop_vision_frame)
 	extend_vision_frame = prepare_vision_frame(extend_vision_frame)
-	extend_vision_frame = forward(crop_vision_frame, extend_vision_frame)
+	age_modifier_direction = numpy.array(numpy.interp(state_manager.get_item('age_modifier_direction'), [ -100, 100 ], [ 2.5, -2.5 ])).astype(numpy.float32)
+	extend_vision_frame = forward(crop_vision_frame, extend_vision_frame, age_modifier_direction)
 	extend_vision_frame = normalize_extend_frame(extend_vision_frame)
-	extend_vision_frame = fix_color(extend_vision_frame_raw, extend_vision_frame)
-	extend_crop_mask = cv2.pyrUp(numpy.minimum.reduce(crop_masks).clip(0, 1))
-	extend_affine_matrix *= extend_vision_frame.shape[0] / 512
-	paste_vision_frame = paste_back(temp_vision_frame, extend_vision_frame, extend_crop_mask, extend_affine_matrix)
+	extend_vision_frame = match_frame_color(extend_vision_frame_raw, extend_vision_frame)
+	extend_affine_matrix *= (model_sizes.get('target')[0] * 4) / model_sizes.get('target_with_background')[0]
+	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
+	crop_mask = cv2.resize(crop_mask, (model_sizes.get('target')[0] * 4, model_sizes.get('target')[1] * 4))
+	paste_vision_frame = paste_back(temp_vision_frame, extend_vision_frame, crop_mask, extend_affine_matrix)
 	return paste_vision_frame
 
 
-def forward(crop_vision_frame : VisionFrame, extend_vision_frame : VisionFrame) -> VisionFrame:
+def forward(crop_vision_frame : VisionFrame, extend_vision_frame : VisionFrame, age_modifier_direction : AgeModifierDirection) -> VisionFrame:
 	age_modifier = get_inference_pool().get('age_modifier')
 	age_modifier_inputs = {}
 
+	if has_execution_provider('coreml'):
+		age_modifier.set_providers([ facefusion.choices.execution_provider_set.get('cpu') ])
+
 	for age_modifier_input in age_modifier.get_inputs():
 		if age_modifier_input.name == 'target':
 			age_modifier_inputs[age_modifier_input.name] = crop_vision_frame
 		if age_modifier_input.name == 'target_with_background':
 			age_modifier_inputs[age_modifier_input.name] = extend_vision_frame
 		if age_modifier_input.name == 'direction':
-			age_modifier_inputs[age_modifier_input.name] = prepare_direction(state_manager.get_item('age_modifier_direction'))
+			age_modifier_inputs[age_modifier_input.name] = age_modifier_direction
 
 	with thread_semaphore():
 		crop_vision_frame = age_modifier.run(None, age_modifier_inputs)[0][0]
@@ -164,38 +181,6 @@ def forward(crop_vision_frame : VisionFrame, extend_vision_frame : VisionFrame)
 	return crop_vision_frame
 
 
-def fix_color(extend_vision_frame_raw : VisionFrame, extend_vision_frame : VisionFrame) -> VisionFrame:
-	color_difference = compute_color_difference(extend_vision_frame_raw, extend_vision_frame, (48, 48))
-	color_difference_mask = create_static_box_mask(extend_vision_frame.shape[:2][::-1], 1.0, (0, 0, 0, 0))
-	color_difference_mask = numpy.stack((color_difference_mask, ) * 3, axis = -1)
-	extend_vision_frame = normalize_color_difference(color_difference, color_difference_mask, extend_vision_frame)
-	return extend_vision_frame
-
-
-def compute_color_difference(extend_vision_frame_raw : VisionFrame, extend_vision_frame : VisionFrame, size : Size) -> VisionFrame:
-	extend_vision_frame_raw = extend_vision_frame_raw.astype(numpy.float32) / 255
-	extend_vision_frame_raw = cv2.resize(extend_vision_frame_raw, size, interpolation = cv2.INTER_AREA)
-	extend_vision_frame = extend_vision_frame.astype(numpy.float32) / 255
-	extend_vision_frame = cv2.resize(extend_vision_frame, size, interpolation = cv2.INTER_AREA)
-	color_difference = extend_vision_frame_raw - extend_vision_frame
-	return color_difference
-
-
-def normalize_color_difference(color_difference : VisionFrame, color_difference_mask : Mask, extend_vision_frame : VisionFrame) -> VisionFrame:
-	color_difference = cv2.resize(color_difference, extend_vision_frame.shape[:2][::-1], interpolation = cv2.INTER_CUBIC)
-	color_difference_mask = 1 - color_difference_mask.clip(0, 0.75)
-	extend_vision_frame = extend_vision_frame.astype(numpy.float32) / 255
-	extend_vision_frame += color_difference * color_difference_mask
-	extend_vision_frame = extend_vision_frame.clip(0, 1)
-	extend_vision_frame = numpy.multiply(extend_vision_frame, 255).astype(numpy.uint8)
-	return extend_vision_frame
-
-
-def prepare_direction(direction : int) -> NDArray[Any]:
-	direction = numpy.interp(float(direction), [ -100, 100 ], [ 2.5, -2.5 ]) #type:ignore[assignment]
-	return numpy.array(direction).astype(numpy.float32)
-
-
 def prepare_vision_frame(vision_frame : VisionFrame) -> VisionFrame:
 	vision_frame = vision_frame[:, :, ::-1] / 255.0
 	vision_frame = (vision_frame - 0.5) / 0.5
@@ -204,12 +189,13 @@ def prepare_vision_frame(vision_frame : VisionFrame) -> VisionFrame:
 
 
 def normalize_extend_frame(extend_vision_frame : VisionFrame) -> VisionFrame:
+	model_sizes = get_model_options().get('sizes')
 	extend_vision_frame = numpy.clip(extend_vision_frame, -1, 1)
 	extend_vision_frame = (extend_vision_frame + 1) / 2
 	extend_vision_frame = extend_vision_frame.transpose(1, 2, 0).clip(0, 255)
 	extend_vision_frame = (extend_vision_frame * 255.0)
 	extend_vision_frame = extend_vision_frame.astype(numpy.uint8)[:, :, ::-1]
-	extend_vision_frame = cv2.pyrDown(extend_vision_frame)
+	extend_vision_frame = cv2.resize(extend_vision_frame, (model_sizes.get('target')[0] * 4, model_sizes.get('target')[1] * 4), interpolation = cv2.INTER_AREA)
 	return extend_vision_frame
 
 

facefusion/processors/modules/deep_swapper.py

@@ -0,0 +1,464 @@
+from argparse import ArgumentParser
+from functools import lru_cache
+from typing import List, Tuple
+
+import cv2
+import numpy
+from cv2.typing import Size
+
+import facefusion.jobs.job_manager
+import facefusion.jobs.job_store
+import facefusion.processors.core as processors
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, wording
+from facefusion.common_helper import create_int_metavar
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url_by_provider
+from facefusion.face_analyser import get_many_faces, get_one_face
+from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
+from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
+from facefusion.face_store import get_reference_faces
+from facefusion.filesystem import get_file_name, in_directory, is_image, is_video, resolve_file_paths, resolve_relative_path, same_file_extension
+from facefusion.processors import choices as processors_choices
+from facefusion.processors.types import DeepSwapperInputs, DeepSwapperMorph
+from facefusion.program_helper import find_argument_group
+from facefusion.thread_helper import thread_semaphore
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, Mask, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.vision import conditional_match_frame_color, read_image, read_static_image, write_image
+
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	model_config = []
+
+	if download_scope == 'full':
+		model_config.extend(
+		[
+			('druuzil', 'adam_levine_320'),
+			('druuzil', 'adrianne_palicki_384'),
+			('druuzil', 'agnetha_falskog_224'),
+			('druuzil', 'alan_ritchson_320'),
+			('druuzil', 'alicia_vikander_320'),
+			('druuzil', 'amber_midthunder_320'),
+			('druuzil', 'andras_arato_384'),
+			('druuzil', 'andrew_tate_320'),
+			('druuzil', 'angelina_jolie_384'),
+			('druuzil', 'anne_hathaway_320'),
+			('druuzil', 'anya_chalotra_320'),
+			('druuzil', 'arnold_schwarzenegger_320'),
+			('druuzil', 'benjamin_affleck_320'),
+			('druuzil', 'benjamin_stiller_384'),
+			('druuzil', 'bradley_pitt_224'),
+			('druuzil', 'brie_larson_384'),
+			('druuzil', 'bruce_campbell_384'),
+			('druuzil', 'bryan_cranston_320'),
+			('druuzil', 'catherine_blanchett_352'),
+			('druuzil', 'christian_bale_320'),
+			('druuzil', 'christopher_hemsworth_320'),
+			('druuzil', 'christoph_waltz_384'),
+			('druuzil', 'cillian_murphy_320'),
+			('druuzil', 'cobie_smulders_256'),
+			('druuzil', 'dwayne_johnson_384'),
+			('druuzil', 'edward_norton_320'),
+			('druuzil', 'elisabeth_shue_320'),
+			('druuzil', 'elizabeth_olsen_384'),
+			('druuzil', 'elon_musk_320'),
+			('druuzil', 'emily_blunt_320'),
+			('druuzil', 'emma_stone_384'),
+			('druuzil', 'emma_watson_320'),
+			('druuzil', 'erin_moriarty_384'),
+			('druuzil', 'eva_green_320'),
+			('druuzil', 'ewan_mcgregor_320'),
+			('druuzil', 'florence_pugh_320'),
+			('druuzil', 'freya_allan_320'),
+			('druuzil', 'gary_cole_224'),
+			('druuzil', 'gigi_hadid_224'),
+			('druuzil', 'harrison_ford_384'),
+			('druuzil', 'hayden_christensen_320'),
+			('druuzil', 'heath_ledger_320'),
+			('druuzil', 'henry_cavill_448'),
+			('druuzil', 'hugh_jackman_384'),
+			('druuzil', 'idris_elba_320'),
+			('druuzil', 'jack_nicholson_320'),
+			('druuzil', 'james_carrey_384'),
+			('druuzil', 'james_mcavoy_320'),
+			('druuzil', 'james_varney_320'),
+			('druuzil', 'jason_momoa_320'),
+			('druuzil', 'jason_statham_320'),
+			('druuzil', 'jennifer_connelly_384'),
+			('druuzil', 'jimmy_donaldson_320'),
+			('druuzil', 'jordan_peterson_384'),
+			('druuzil', 'karl_urban_224'),
+			('druuzil', 'kate_beckinsale_384'),
+			('druuzil', 'laurence_fishburne_384'),
+			('druuzil', 'lili_reinhart_320'),
+			('druuzil', 'luke_evans_384'),
+			('druuzil', 'mads_mikkelsen_384'),
+			('druuzil', 'mary_winstead_320'),
+			('druuzil', 'margaret_qualley_384'),
+			('druuzil', 'melina_juergens_320'),
+			('druuzil', 'michael_fassbender_320'),
+			('druuzil', 'michael_fox_320'),
+			('druuzil', 'millie_bobby_brown_320'),
+			('druuzil', 'morgan_freeman_320'),
+			('druuzil', 'patrick_stewart_224'),
+			('druuzil', 'rachel_weisz_384'),
+			('druuzil', 'rebecca_ferguson_320'),
+			('druuzil', 'scarlett_johansson_320'),
+			('druuzil', 'shannen_doherty_384'),
+			('druuzil', 'seth_macfarlane_384'),
+			('druuzil', 'thomas_cruise_320'),
+			('druuzil', 'thomas_hanks_384'),
+			('druuzil', 'william_murray_384'),
+			('druuzil', 'zoe_saldana_384'),
+			('edel', 'emma_roberts_224'),
+			('edel', 'ivanka_trump_224'),
+			('edel', 'lize_dzjabrailova_224'),
+			('edel', 'sidney_sweeney_224'),
+			('edel', 'winona_ryder_224')
+		])
+	if download_scope in [ 'lite', 'full' ]:
+		model_config.extend(
+		[
+			('iperov', 'alexandra_daddario_224'),
+			('iperov', 'alexei_navalny_224'),
+			('iperov', 'amber_heard_224'),
+			('iperov', 'dilraba_dilmurat_224'),
+			('iperov', 'elon_musk_224'),
+			('iperov', 'emilia_clarke_224'),
+			('iperov', 'emma_watson_224'),
+			('iperov', 'erin_moriarty_224'),
+			('iperov', 'jackie_chan_224'),
+			('iperov', 'james_carrey_224'),
+			('iperov', 'jason_statham_320'),
+			('iperov', 'keanu_reeves_320'),
+			('iperov', 'margot_robbie_224'),
+			('iperov', 'natalie_dormer_224'),
+			('iperov', 'nicolas_coppola_224'),
+			('iperov', 'robert_downey_224'),
+			('iperov', 'rowan_atkinson_224'),
+			('iperov', 'ryan_reynolds_224'),
+			('iperov', 'scarlett_johansson_224'),
+			('iperov', 'sylvester_stallone_224'),
+			('iperov', 'thomas_cruise_224'),
+			('iperov', 'thomas_holland_224'),
+			('iperov', 'vin_diesel_224'),
+			('iperov', 'vladimir_putin_224')
+		])
+	if download_scope == 'full':
+		model_config.extend(
+		[
+			('jen', 'angelica_trae_288'),
+			('jen', 'ella_freya_224'),
+			('jen', 'emma_myers_320'),
+			('jen', 'evie_pickerill_224'),
+			('jen', 'kang_hyewon_320'),
+			('jen', 'maddie_mead_224'),
+			('jen', 'nicole_turnbull_288'),
+			('mats', 'alica_schmidt_320'),
+			('mats', 'ashley_alexiss_224'),
+			('mats', 'billie_eilish_224'),
+			('mats', 'brie_larson_224'),
+			('mats', 'cara_delevingne_224'),
+			('mats', 'carolin_kebekus_224'),
+			('mats', 'chelsea_clinton_224'),
+			('mats', 'claire_boucher_224'),
+			('mats', 'corinna_kopf_224'),
+			('mats', 'florence_pugh_224'),
+			('mats', 'hillary_clinton_224'),
+			('mats', 'jenna_fischer_224'),
+			('mats', 'kim_jisoo_320'),
+			('mats', 'mica_suarez_320'),
+			('mats', 'shailene_woodley_224'),
+			('mats', 'shraddha_kapoor_320'),
+			('mats', 'yu_jimin_352'),
+			('rumateus', 'alison_brie_224'),
+			('rumateus', 'amber_heard_224'),
+			('rumateus', 'angelina_jolie_224'),
+			('rumateus', 'aubrey_plaza_224'),
+			('rumateus', 'bridget_regan_224'),
+			('rumateus', 'cobie_smulders_224'),
+			('rumateus', 'deborah_woll_224'),
+			('rumateus', 'dua_lipa_224'),
+			('rumateus', 'emma_stone_224'),
+			('rumateus', 'hailee_steinfeld_224'),
+			('rumateus', 'hilary_duff_224'),
+			('rumateus', 'jessica_alba_224'),
+			('rumateus', 'jessica_biel_224'),
+			('rumateus', 'john_cena_224'),
+			('rumateus', 'kim_kardashian_224'),
+			('rumateus', 'kristen_bell_224'),
+			('rumateus', 'lucy_liu_224'),
+			('rumateus', 'margot_robbie_224'),
+			('rumateus', 'megan_fox_224'),
+			('rumateus', 'meghan_markle_224'),
+			('rumateus', 'millie_bobby_brown_224'),
+			('rumateus', 'natalie_portman_224'),
+			('rumateus', 'nicki_minaj_224'),
+			('rumateus', 'olivia_wilde_224'),
+			('rumateus', 'shay_mitchell_224'),
+			('rumateus', 'sophie_turner_224'),
+			('rumateus', 'taylor_swift_224')
+		])
+	model_set : ModelSet = {}
+
+	for model_scope, model_name in model_config:
+		model_id = '/'.join([ model_scope, model_name ])
+
+		model_set[model_id] =\
+		{
+			'hashes':
+			{
+				'deep_swapper':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'deepfacelive-models-' + model_scope, model_name + '.hash'),
+					'path': resolve_relative_path('../.assets/models/' + model_scope + '/' + model_name + '.hash')
+				}
+			},
+			'sources':
+			{
+				'deep_swapper':
+				{
+					'url': resolve_download_url_by_provider('huggingface', 'deepfacelive-models-' + model_scope, model_name + '.dfm'),
+					'path': resolve_relative_path('../.assets/models/' + model_scope + '/' + model_name + '.dfm')
+				}
+			},
+			'template': 'dfl_whole_face'
+		}
+
+	custom_model_file_paths = resolve_file_paths(resolve_relative_path('../.assets/models/custom'))
+
+	if custom_model_file_paths:
+
+		for model_file_path in custom_model_file_paths:
+			model_id = '/'.join([ 'custom', get_file_name(model_file_path) ])
+
+			model_set[model_id] =\
+			{
+				'sources':
+				{
+					'deep_swapper':
+					{
+						'path': resolve_relative_path(model_file_path)
+					}
+				},
+				'template': 'dfl_whole_face'
+			}
+
+	return model_set
+
+
+def get_inference_pool() -> InferencePool:
+	model_names = [ state_manager.get_item('deep_swapper_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
+
+
+def clear_inference_pool() -> None:
+	model_names = [ state_manager.get_item('deep_swapper_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
+
+
+def get_model_options() -> ModelOptions:
+	model_name = state_manager.get_item('deep_swapper_model')
+	return create_static_model_set('full').get(model_name)
+
+
+def get_model_size() -> Size:
+	deep_swapper = get_inference_pool().get('deep_swapper')
+
+	for deep_swapper_input in deep_swapper.get_inputs():
+		if deep_swapper_input.name == 'in_face:0':
+			return deep_swapper_input.shape[1:3]
+
+	return 0, 0
+
+
+def register_args(program : ArgumentParser) -> None:
+	group_processors = find_argument_group(program, 'processors')
+	if group_processors:
+		group_processors.add_argument('--deep-swapper-model', help = wording.get('help.deep_swapper_model'), default = config.get_str_value('processors', 'deep_swapper_model', 'iperov/elon_musk_224'), choices = processors_choices.deep_swapper_models)
+		group_processors.add_argument('--deep-swapper-morph', help = wording.get('help.deep_swapper_morph'), type = int, default = config.get_int_value('processors', 'deep_swapper_morph', '100'), choices = processors_choices.deep_swapper_morph_range, metavar = create_int_metavar(processors_choices.deep_swapper_morph_range))
+		facefusion.jobs.job_store.register_step_keys([ 'deep_swapper_model', 'deep_swapper_morph' ])
+
+
+def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
+	apply_state_item('deep_swapper_model', args.get('deep_swapper_model'))
+	apply_state_item('deep_swapper_morph', args.get('deep_swapper_morph'))
+
+
+def pre_check() -> bool:
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
+
+	if model_hash_set and model_source_set:
+		return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
+	return True
+
+
+def pre_process(mode : ProcessMode) -> bool:
+	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
+		logger.error(wording.get('choose_image_or_video_target') + wording.get('exclamation_mark'), __name__)
+		return False
+	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
+		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
+		return False
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
+		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
+		return False
+	return True
+
+
+def post_process() -> None:
+	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
+	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
+		clear_inference_pool()
+	if state_manager.get_item('video_memory_strategy') == 'strict':
+		content_analyser.clear_inference_pool()
+		face_classifier.clear_inference_pool()
+		face_detector.clear_inference_pool()
+		face_landmarker.clear_inference_pool()
+		face_masker.clear_inference_pool()
+		face_recognizer.clear_inference_pool()
+
+
+def swap_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	model_template = get_model_options().get('template')
+	model_size = get_model_size()
+	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
+	crop_vision_frame_raw = crop_vision_frame.copy()
+	box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
+	crop_masks =\
+	[
+		box_mask
+	]
+
+	if 'occlusion' in state_manager.get_item('face_mask_types'):
+		occlusion_mask = create_occlusion_mask(crop_vision_frame)
+		crop_masks.append(occlusion_mask)
+
+	crop_vision_frame = prepare_crop_frame(crop_vision_frame)
+	deep_swapper_morph = numpy.array([ numpy.interp(state_manager.get_item('deep_swapper_morph'), [ 0, 100 ], [ 0, 1 ]) ]).astype(numpy.float32)
+	crop_vision_frame, crop_source_mask, crop_target_mask = forward(crop_vision_frame, deep_swapper_morph)
+	crop_vision_frame = normalize_crop_frame(crop_vision_frame)
+	crop_vision_frame = conditional_match_frame_color(crop_vision_frame_raw, crop_vision_frame)
+	crop_masks.append(prepare_crop_mask(crop_source_mask, crop_target_mask))
+
+	if 'area' in state_manager.get_item('face_mask_types'):
+		face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		area_mask = create_area_mask(crop_vision_frame, face_landmark_68, state_manager.get_item('face_mask_areas'))
+		crop_masks.append(area_mask)
+
+	if 'region' in state_manager.get_item('face_mask_types'):
+		region_mask = create_region_mask(crop_vision_frame, state_manager.get_item('face_mask_regions'))
+		crop_masks.append(region_mask)
+
+	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
+	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
+	return paste_vision_frame
+
+
+def forward(crop_vision_frame : VisionFrame, deep_swapper_morph : DeepSwapperMorph) -> Tuple[VisionFrame, Mask, Mask]:
+	deep_swapper = get_inference_pool().get('deep_swapper')
+	deep_swapper_inputs = {}
+
+	for deep_swapper_input in deep_swapper.get_inputs():
+		if deep_swapper_input.name == 'in_face:0':
+			deep_swapper_inputs[deep_swapper_input.name] = crop_vision_frame
+		if deep_swapper_input.name == 'morph_value:0':
+			deep_swapper_inputs[deep_swapper_input.name] = deep_swapper_morph
+
+	with thread_semaphore():
+		crop_target_mask, crop_vision_frame, crop_source_mask = deep_swapper.run(None, deep_swapper_inputs)
+
+	return crop_vision_frame[0], crop_source_mask[0], crop_target_mask[0]
+
+
+def has_morph_input() -> bool:
+	deep_swapper = get_inference_pool().get('deep_swapper')
+
+	for deep_swapper_input in deep_swapper.get_inputs():
+		if deep_swapper_input.name == 'morph_value:0':
+			return True
+
+	return False
+
+
+def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	crop_vision_frame = cv2.addWeighted(crop_vision_frame, 1.75, cv2.GaussianBlur(crop_vision_frame, (0, 0), 2), -0.75, 0)
+	crop_vision_frame = crop_vision_frame / 255.0
+	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0).astype(numpy.float32)
+	return crop_vision_frame
+
+
+def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	crop_vision_frame = (crop_vision_frame * 255.0).clip(0, 255)
+	crop_vision_frame = crop_vision_frame.astype(numpy.uint8)
+	return crop_vision_frame
+
+
+def prepare_crop_mask(crop_source_mask : Mask, crop_target_mask : Mask) -> Mask:
+	model_size = get_model_size()
+	blur_size = 6.25
+	kernel_size = 3
+	crop_mask = numpy.minimum.reduce([ crop_source_mask, crop_target_mask ])
+	crop_mask = crop_mask.reshape(model_size).clip(0, 1)
+	crop_mask = cv2.erode(crop_mask, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (kernel_size, kernel_size)), iterations = 2)
+	crop_mask = cv2.GaussianBlur(crop_mask, (0, 0), blur_size)
+	return crop_mask
+
+
+def get_reference_frame(source_face : Face, target_face : Face, temp_vision_frame : VisionFrame) -> VisionFrame:
+	return swap_face(target_face, temp_vision_frame)
+
+
+def process_frame(inputs : DeepSwapperInputs) -> VisionFrame:
+	reference_faces = inputs.get('reference_faces')
+	target_vision_frame = inputs.get('target_vision_frame')
+	many_faces = sort_and_filter_faces(get_many_faces([ target_vision_frame ]))
+
+	if state_manager.get_item('face_selector_mode') == 'many':
+		if many_faces:
+			for target_face in many_faces:
+				target_vision_frame = swap_face(target_face, target_vision_frame)
+	if state_manager.get_item('face_selector_mode') == 'one':
+		target_face = get_one_face(many_faces)
+		if target_face:
+			target_vision_frame = swap_face(target_face, target_vision_frame)
+	if state_manager.get_item('face_selector_mode') == 'reference':
+		similar_faces = find_similar_faces(many_faces, reference_faces, state_manager.get_item('reference_face_distance'))
+		if similar_faces:
+			for similar_face in similar_faces:
+				target_vision_frame = swap_face(similar_face, target_vision_frame)
+	return target_vision_frame
+
+
+def process_frames(source_path : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
+	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
+
+	for queue_payload in process_manager.manage(queue_payloads):
+		target_vision_path = queue_payload['frame_path']
+		target_vision_frame = read_image(target_vision_path)
+		output_vision_frame = process_frame(
+		{
+			'reference_faces': reference_faces,
+			'target_vision_frame': target_vision_frame
+		})
+		write_image(target_vision_path, output_vision_frame)
+		update_progress(1)
+
+
+def process_image(source_path : str, target_path : str, output_path : str) -> None:
+	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
+	target_vision_frame = read_static_image(target_path)
+	output_vision_frame = process_frame(
+	{
+		'reference_faces': reference_faces,
+		'target_vision_frame': target_vision_frame
+	})
+	write_image(output_path, output_vision_frame)
+
+
+def process_video(source_paths : List[str], temp_frame_paths : List[str]) -> None:
+	processors.multi_process_frames(None, temp_frame_paths, process_frames)

facefusion/processors/modules/expression_restorer.py

@@ -1,4 +1,5 @@
 from argparse import ArgumentParser
+from functools import lru_cache
 from typing import List, Tuple
 
 import cv2
@@ -7,91 +8,95 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, wording
 from facefusion.common_helper import create_int_metavar
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_analyser import get_many_faces, get_one_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_static_box_mask
+from facefusion.face_masker import create_box_mask, create_occlusion_mask
 from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
 from facefusion.face_store import get_reference_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.live_portrait import create_rotation, limit_expression
-from facefusion.processors.typing import ExpressionRestorerInputs
-from facefusion.processors.typing import LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
+from facefusion.processors.types import ExpressionRestorerInputs, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore, thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
-from facefusion.vision import get_video_frame, read_image, read_static_image, write_image
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.vision import read_image, read_static_image, read_video_frame, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'live_portrait':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'live_portrait':
 		{
-			'feature_extractor':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_feature_extractor.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.hash')
+				'feature_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_feature_extractor.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.hash')
+				},
+				'motion_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_motion_extractor.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.hash')
+				},
+				'generator':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_generator.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_generator.hash')
+				}
 			},
-			'motion_extractor':
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_motion_extractor.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.hash')
+				'feature_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_feature_extractor.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.onnx')
+				},
+				'motion_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_motion_extractor.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.onnx')
+				},
+				'generator':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_generator.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_generator.onnx')
+				}
 			},
-			'generator':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_generator.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_generator.hash')
-			}
-		},
-		'sources':
-		{
-			'feature_extractor':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_feature_extractor.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.onnx')
-			},
-			'motion_extractor':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_motion_extractor.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.onnx')
-			},
-			'generator':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_generator.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_generator.onnx')
-			}
-		},
-		'template': 'arcface_128_v2',
-		'size': (512, 512)
+			'template': 'arcface_128',
+			'size': (512, 512)
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('expression_restorer_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('expression_restorer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	inference_manager.clear_inference_pool(__name__)
+	model_names = [ state_manager.get_item('expression_restorer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	expression_restorer_model = state_manager.get_item('expression_restorer_model')
-	return MODEL_SET.get(expression_restorer_model)
+	model_name = state_manager.get_item('expression_restorer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--expression-restorer-model', help = wording.get('help.expression_restorer_model'), default = config.get_str_value('processors.expression_restorer_model', 'live_portrait'), choices = processors_choices.expression_restorer_models)
-		group_processors.add_argument('--expression-restorer-factor', help = wording.get('help.expression_restorer_factor'), type = int, default = config.get_int_value('processors.expression_restorer_factor', '80'), choices = processors_choices.expression_restorer_factor_range, metavar = create_int_metavar(processors_choices.expression_restorer_factor_range))
-		facefusion.jobs.job_store.register_step_keys([ 'expression_restorer_model','expression_restorer_factor' ])
+		group_processors.add_argument('--expression-restorer-model', help = wording.get('help.expression_restorer_model'), default = config.get_str_value('processors', 'expression_restorer_model', 'live_portrait'), choices = processors_choices.expression_restorer_models)
+		group_processors.add_argument('--expression-restorer-factor', help = wording.get('help.expression_restorer_factor'), type = int, default = config.get_int_value('processors', 'expression_restorer_factor', '80'), choices = processors_choices.expression_restorer_factor_range, metavar = create_int_metavar(processors_choices.expression_restorer_factor_range))
+		facefusion.jobs.job_store.register_step_keys([ 'expression_restorer_model', 'expression_restorer_factor' ])
 
 
 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
@@ -100,21 +105,23 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
+	if mode == 'stream':
+		logger.error(wording.get('stream_not_supported') + wording.get('exclamation_mark'), __name__)
+		return False
 	if mode in [ 'output', 'preview' ] and not is_image(state_manager.get_item('target_path')) and not is_video(state_manager.get_item('target_path')):
 		logger.error(wording.get('choose_image_or_video_target') + wording.get('exclamation_mark'), __name__)
 		return False
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -122,6 +129,7 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -140,7 +148,7 @@ def restore_expression(source_vision_frame : VisionFrame, target_face : Face, te
 	source_vision_frame = cv2.resize(source_vision_frame, temp_vision_frame.shape[:2][::-1])
 	source_crop_vision_frame, _ = warp_face_by_face_landmark_5(source_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
 	target_crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
-	box_mask = create_static_box_mask(target_crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	box_mask = create_box_mask(target_crop_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_masks =\
 	[
 		box_mask
@@ -222,7 +230,7 @@ def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 
 def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 	crop_vision_frame = crop_vision_frame.transpose(1, 2, 0).clip(0, 1)
-	crop_vision_frame = (crop_vision_frame * 255.0)
+	crop_vision_frame = crop_vision_frame * 255.0
 	crop_vision_frame = crop_vision_frame.astype(numpy.uint8)[:, :, ::-1]
 	return crop_vision_frame
 
@@ -260,7 +268,7 @@ def process_frames(source_path : List[str], queue_payloads : List[QueuePayload],
 		frame_number = queue_payload.get('frame_number')
 		if state_manager.get_item('trim_frame_start'):
 			frame_number += state_manager.get_item('trim_frame_start')
-		source_vision_frame = get_video_frame(state_manager.get_item('target_path'), frame_number)
+		source_vision_frame = read_video_frame(state_manager.get_item('target_path'), frame_number)
 		target_vision_path = queue_payload.get('frame_path')
 		target_vision_frame = read_image(target_vision_path)
 		output_vision_frame = process_frame(

facefusion/processors/modules/face_debugger.py

@@ -7,21 +7,21 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, logger, process_manager, state_manager, video_manager, wording
 from facefusion.face_analyser import get_many_faces, get_one_face
 from facefusion.face_helper import warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_region_mask, create_static_box_mask
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
 from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
 from facefusion.face_store import get_reference_faces
 from facefusion.filesystem import in_directory, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FaceDebuggerInputs
+from facefusion.processors.types import FaceDebuggerInputs
 from facefusion.program_helper import find_argument_group
-from facefusion.typing import ApplyStateItem, Args, Face, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.types import ApplyStateItem, Args, Face, InferencePool, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
 from facefusion.vision import read_image, read_static_image, write_image
 
 
-def get_inference_pool() -> None:
+def get_inference_pool() -> InferencePool:
 	pass
 
 
@@ -32,7 +32,7 @@ def clear_inference_pool() -> None:
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-debugger-items', help = wording.get('help.face_debugger_items').format(choices = ', '.join(processors_choices.face_debugger_items)), default = config.get_str_list('processors.face_debugger_items', 'face-landmark-5/68 face-mask'), choices = processors_choices.face_debugger_items, nargs = '+', metavar = 'FACE_DEBUGGER_ITEMS')
+		group_processors.add_argument('--face-debugger-items', help = wording.get('help.face_debugger_items').format(choices = ', '.join(processors_choices.face_debugger_items)), default = config.get_str_list('processors', 'face_debugger_items', 'face-landmark-5/68 face-mask'), choices = processors_choices.face_debugger_items, nargs = '+', metavar = 'FACE_DEBUGGER_ITEMS')
 		facefusion.jobs.job_store.register_step_keys([ 'face_debugger_items' ])
 
 
@@ -48,7 +48,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -56,6 +56,7 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
 		content_analyser.clear_inference_pool()
 		face_classifier.clear_inference_pool()
@@ -82,27 +83,32 @@ def debug_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFra
 
 		if target_face.angle == 0:
 			cv2.line(temp_vision_frame, (x1, y1), (x2, y1), primary_light_color, 3)
-		elif target_face.angle == 180:
+		if target_face.angle == 180:
 			cv2.line(temp_vision_frame, (x1, y2), (x2, y2), primary_light_color, 3)
-		elif target_face.angle == 90:
+		if target_face.angle == 90:
 			cv2.line(temp_vision_frame, (x2, y1), (x2, y2), primary_light_color, 3)
-		elif target_face.angle == 270:
+		if target_face.angle == 270:
 			cv2.line(temp_vision_frame, (x1, y1), (x1, y2), primary_light_color, 3)
 
 	if 'face-mask' in face_debugger_items:
-		crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), 'arcface_128_v2', (512, 512))
+		crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), 'arcface_128', (512, 512))
 		inverse_matrix = cv2.invertAffineTransform(affine_matrix)
 		temp_size = temp_vision_frame.shape[:2][::-1]
 		crop_masks = []
 
 		if 'box' in state_manager.get_item('face_mask_types'):
-			box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], 0, state_manager.get_item('face_mask_padding'))
+			box_mask = create_box_mask(crop_vision_frame, 0, state_manager.get_item('face_mask_padding'))
 			crop_masks.append(box_mask)
 
 		if 'occlusion' in state_manager.get_item('face_mask_types'):
 			occlusion_mask = create_occlusion_mask(crop_vision_frame)
 			crop_masks.append(occlusion_mask)
 
+		if 'area' in state_manager.get_item('face_mask_types'):
+			face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+			area_mask = create_area_mask(crop_vision_frame, face_landmark_68, state_manager.get_item('face_mask_areas'))
+			crop_masks.append(area_mask)
+
 		if 'region' in state_manager.get_item('face_mask_types'):
 			region_mask = create_region_mask(crop_vision_frame, state_manager.get_item('face_mask_regions'))
 			crop_masks.append(region_mask)

facefusion/processors/modules/face_editor.py

@@ -1,4 +1,5 @@
 from argparse import ArgumentParser
+from functools import lru_cache
 from typing import List, Tuple
 
 import cv2
@@ -7,133 +8,137 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, wording
 from facefusion.common_helper import create_float_metavar
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_analyser import get_many_faces, get_one_face
 from facefusion.face_helper import paste_back, scale_face_landmark_5, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_static_box_mask
+from facefusion.face_masker import create_box_mask
 from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
 from facefusion.face_store import get_reference_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.live_portrait import create_rotation, limit_euler_angles, limit_expression
-from facefusion.processors.typing import FaceEditorInputs, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
+from facefusion.processors.types import FaceEditorInputs, LivePortraitExpression, LivePortraitFeatureVolume, LivePortraitMotionPoints, LivePortraitPitch, LivePortraitRoll, LivePortraitRotation, LivePortraitScale, LivePortraitTranslation, LivePortraitYaw
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore, thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, Face, FaceLandmark68, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, FaceLandmark68, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
 from facefusion.vision import read_image, read_static_image, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'live_portrait':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'live_portrait':
 		{
-			'feature_extractor':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_feature_extractor.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.hash')
+				'feature_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_feature_extractor.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.hash')
+				},
+				'motion_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_motion_extractor.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.hash')
+				},
+				'eye_retargeter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_eye_retargeter.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_eye_retargeter.hash')
+				},
+				'lip_retargeter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_lip_retargeter.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_lip_retargeter.hash')
+				},
+				'stitcher':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_stitcher.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_stitcher.hash')
+				},
+				'generator':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_generator.hash'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_generator.hash')
+				}
 			},
-			'motion_extractor':
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_motion_extractor.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.hash')
+				'feature_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_feature_extractor.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.onnx')
+				},
+				'motion_extractor':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_motion_extractor.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.onnx')
+				},
+				'eye_retargeter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_eye_retargeter.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_eye_retargeter.onnx')
+				},
+				'lip_retargeter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_lip_retargeter.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_lip_retargeter.onnx')
+				},
+				'stitcher':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_stitcher.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_stitcher.onnx')
+				},
+				'generator':
+				{
+					'url': resolve_download_url('models-3.0.0', 'live_portrait_generator.onnx'),
+					'path': resolve_relative_path('../.assets/models/live_portrait_generator.onnx')
+				}
 			},
-			'eye_retargeter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_eye_retargeter.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_eye_retargeter.hash')
-			},
-			'lip_retargeter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_lip_retargeter.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_lip_retargeter.hash')
-			},
-			'stitcher':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_stitcher.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_stitcher.hash')
-			},
-			'generator':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_generator.hash',
-				'path': resolve_relative_path('../.assets/models/live_portrait_generator.hash')
-			}
-		},
-		'sources':
-		{
-			'feature_extractor':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_feature_extractor.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_feature_extractor.onnx')
-			},
-			'motion_extractor':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_motion_extractor.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_motion_extractor.onnx')
-			},
-			'eye_retargeter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_eye_retargeter.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_eye_retargeter.onnx')
-			},
-			'lip_retargeter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_lip_retargeter.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_lip_retargeter.onnx')
-			},
-			'stitcher':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_stitcher.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_stitcher.onnx')
-			},
-			'generator':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/live_portrait_generator.onnx',
-				'path': resolve_relative_path('../.assets/models/live_portrait_generator.onnx')
-			}
-		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
+			'template': 'ffhq_512',
+			'size': (512, 512)
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('face_editor_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('face_editor_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('face_editor_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ state_manager.get_item('face_editor_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	face_editor_model = state_manager.get_item('face_editor_model')
-	return MODEL_SET.get(face_editor_model)
+	model_name = state_manager.get_item('face_editor_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-editor-model', help = wording.get('help.face_editor_model'), default = config.get_str_value('processors.face_editor_model', 'live_portrait'), choices = processors_choices.face_editor_models)
-		group_processors.add_argument('--face-editor-eyebrow-direction', help = wording.get('help.face_editor_eyebrow_direction'), type = float, default = config.get_float_value('processors.face_editor_eyebrow_direction', '0'), choices = processors_choices.face_editor_eyebrow_direction_range, metavar = create_float_metavar(processors_choices.face_editor_eyebrow_direction_range))
-		group_processors.add_argument('--face-editor-eye-gaze-horizontal', help = wording.get('help.face_editor_eye_gaze_horizontal'), type = float, default = config.get_float_value('processors.face_editor_eye_gaze_horizontal', '0'), choices = processors_choices.face_editor_eye_gaze_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_horizontal_range))
-		group_processors.add_argument('--face-editor-eye-gaze-vertical', help = wording.get('help.face_editor_eye_gaze_vertical'), type = float, default = config.get_float_value('processors.face_editor_eye_gaze_vertical', '0'), choices = processors_choices.face_editor_eye_gaze_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_vertical_range))
-		group_processors.add_argument('--face-editor-eye-open-ratio', help = wording.get('help.face_editor_eye_open_ratio'), type = float, default = config.get_float_value('processors.face_editor_eye_open_ratio', '0'), choices = processors_choices.face_editor_eye_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_eye_open_ratio_range))
-		group_processors.add_argument('--face-editor-lip-open-ratio', help = wording.get('help.face_editor_lip_open_ratio'), type = float, default = config.get_float_value('processors.face_editor_lip_open_ratio', '0'), choices = processors_choices.face_editor_lip_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_lip_open_ratio_range))
-		group_processors.add_argument('--face-editor-mouth-grim', help = wording.get('help.face_editor_mouth_grim'), type = float, default = config.get_float_value('processors.face_editor_mouth_grim', '0'), choices = processors_choices.face_editor_mouth_grim_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_grim_range))
-		group_processors.add_argument('--face-editor-mouth-pout', help = wording.get('help.face_editor_mouth_pout'), type = float, default = config.get_float_value('processors.face_editor_mouth_pout', '0'), choices = processors_choices.face_editor_mouth_pout_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_pout_range))
-		group_processors.add_argument('--face-editor-mouth-purse', help = wording.get('help.face_editor_mouth_purse'), type = float, default = config.get_float_value('processors.face_editor_mouth_purse', '0'), choices = processors_choices.face_editor_mouth_purse_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_purse_range))
-		group_processors.add_argument('--face-editor-mouth-smile', help = wording.get('help.face_editor_mouth_smile'), type = float, default = config.get_float_value('processors.face_editor_mouth_smile', '0'), choices = processors_choices.face_editor_mouth_smile_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_smile_range))
-		group_processors.add_argument('--face-editor-mouth-position-horizontal', help = wording.get('help.face_editor_mouth_position_horizontal'), type = float, default = config.get_float_value('processors.face_editor_mouth_position_horizontal', '0'), choices = processors_choices.face_editor_mouth_position_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_horizontal_range))
-		group_processors.add_argument('--face-editor-mouth-position-vertical', help = wording.get('help.face_editor_mouth_position_vertical'), type = float, default = config.get_float_value('processors.face_editor_mouth_position_vertical', '0'), choices = processors_choices.face_editor_mouth_position_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_vertical_range))
-		group_processors.add_argument('--face-editor-head-pitch', help = wording.get('help.face_editor_head_pitch'), type = float, default = config.get_float_value('processors.face_editor_head_pitch', '0'), choices = processors_choices.face_editor_head_pitch_range, metavar = create_float_metavar(processors_choices.face_editor_head_pitch_range))
-		group_processors.add_argument('--face-editor-head-yaw', help = wording.get('help.face_editor_head_yaw'), type = float, default = config.get_float_value('processors.face_editor_head_yaw', '0'), choices = processors_choices.face_editor_head_yaw_range, metavar = create_float_metavar(processors_choices.face_editor_head_yaw_range))
-		group_processors.add_argument('--face-editor-head-roll', help = wording.get('help.face_editor_head_roll'), type = float, default = config.get_float_value('processors.face_editor_head_roll', '0'), choices = processors_choices.face_editor_head_roll_range, metavar = create_float_metavar(processors_choices.face_editor_head_roll_range))
+		group_processors.add_argument('--face-editor-model', help = wording.get('help.face_editor_model'), default = config.get_str_value('processors', 'face_editor_model', 'live_portrait'), choices = processors_choices.face_editor_models)
+		group_processors.add_argument('--face-editor-eyebrow-direction', help = wording.get('help.face_editor_eyebrow_direction'), type = float, default = config.get_float_value('processors', 'face_editor_eyebrow_direction', '0'), choices = processors_choices.face_editor_eyebrow_direction_range, metavar = create_float_metavar(processors_choices.face_editor_eyebrow_direction_range))
+		group_processors.add_argument('--face-editor-eye-gaze-horizontal', help = wording.get('help.face_editor_eye_gaze_horizontal'), type = float, default = config.get_float_value('processors', 'face_editor_eye_gaze_horizontal', '0'), choices = processors_choices.face_editor_eye_gaze_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_horizontal_range))
+		group_processors.add_argument('--face-editor-eye-gaze-vertical', help = wording.get('help.face_editor_eye_gaze_vertical'), type = float, default = config.get_float_value('processors', 'face_editor_eye_gaze_vertical', '0'), choices = processors_choices.face_editor_eye_gaze_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_eye_gaze_vertical_range))
+		group_processors.add_argument('--face-editor-eye-open-ratio', help = wording.get('help.face_editor_eye_open_ratio'), type = float, default = config.get_float_value('processors', 'face_editor_eye_open_ratio', '0'), choices = processors_choices.face_editor_eye_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_eye_open_ratio_range))
+		group_processors.add_argument('--face-editor-lip-open-ratio', help = wording.get('help.face_editor_lip_open_ratio'), type = float, default = config.get_float_value('processors', 'face_editor_lip_open_ratio', '0'), choices = processors_choices.face_editor_lip_open_ratio_range, metavar = create_float_metavar(processors_choices.face_editor_lip_open_ratio_range))
+		group_processors.add_argument('--face-editor-mouth-grim', help = wording.get('help.face_editor_mouth_grim'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_grim', '0'), choices = processors_choices.face_editor_mouth_grim_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_grim_range))
+		group_processors.add_argument('--face-editor-mouth-pout', help = wording.get('help.face_editor_mouth_pout'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_pout', '0'), choices = processors_choices.face_editor_mouth_pout_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_pout_range))
+		group_processors.add_argument('--face-editor-mouth-purse', help = wording.get('help.face_editor_mouth_purse'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_purse', '0'), choices = processors_choices.face_editor_mouth_purse_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_purse_range))
+		group_processors.add_argument('--face-editor-mouth-smile', help = wording.get('help.face_editor_mouth_smile'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_smile', '0'), choices = processors_choices.face_editor_mouth_smile_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_smile_range))
+		group_processors.add_argument('--face-editor-mouth-position-horizontal', help = wording.get('help.face_editor_mouth_position_horizontal'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_position_horizontal', '0'), choices = processors_choices.face_editor_mouth_position_horizontal_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_horizontal_range))
+		group_processors.add_argument('--face-editor-mouth-position-vertical', help = wording.get('help.face_editor_mouth_position_vertical'), type = float, default = config.get_float_value('processors', 'face_editor_mouth_position_vertical', '0'), choices = processors_choices.face_editor_mouth_position_vertical_range, metavar = create_float_metavar(processors_choices.face_editor_mouth_position_vertical_range))
+		group_processors.add_argument('--face-editor-head-pitch', help = wording.get('help.face_editor_head_pitch'), type = float, default = config.get_float_value('processors', 'face_editor_head_pitch', '0'), choices = processors_choices.face_editor_head_pitch_range, metavar = create_float_metavar(processors_choices.face_editor_head_pitch_range))
+		group_processors.add_argument('--face-editor-head-yaw', help = wording.get('help.face_editor_head_yaw'), type = float, default = config.get_float_value('processors', 'face_editor_head_yaw', '0'), choices = processors_choices.face_editor_head_yaw_range, metavar = create_float_metavar(processors_choices.face_editor_head_yaw_range))
+		group_processors.add_argument('--face-editor-head-roll', help = wording.get('help.face_editor_head_roll'), type = float, default = config.get_float_value('processors', 'face_editor_head_roll', '0'), choices = processors_choices.face_editor_head_roll_range, metavar = create_float_metavar(processors_choices.face_editor_head_roll_range))
 		facefusion.jobs.job_store.register_step_keys([ 'face_editor_model', 'face_editor_eyebrow_direction', 'face_editor_eye_gaze_horizontal', 'face_editor_eye_gaze_vertical', 'face_editor_eye_open_ratio', 'face_editor_lip_open_ratio', 'face_editor_mouth_grim', 'face_editor_mouth_pout', 'face_editor_mouth_purse', 'face_editor_mouth_smile', 'face_editor_mouth_position_horizontal', 'face_editor_mouth_position_vertical', 'face_editor_head_pitch', 'face_editor_head_yaw', 'face_editor_head_roll' ])
 
 
@@ -156,11 +161,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -170,7 +174,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -178,6 +182,7 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -194,7 +199,7 @@ def edit_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionFram
 	model_size = get_model_options().get('size')
 	face_landmark_5 = scale_face_landmark_5(target_face.landmark_set.get('5/68'), 1.5)
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, face_landmark_5, model_template, model_size)
-	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_vision_frame = prepare_crop_frame(crop_vision_frame)
 	crop_vision_frame = apply_edit(crop_vision_frame, target_face.landmark_set.get('68'))
 	crop_vision_frame = normalize_crop_frame(crop_vision_frame)
@@ -359,7 +364,7 @@ def edit_lip_open(motion_points : LivePortraitMotionPoints, face_landmark_68 : F
 	else:
 		lip_motion_points = numpy.concatenate([ motion_points.ravel(), [ lip_ratio, 1.0 ] ])
 	lip_motion_points = lip_motion_points.reshape(1, -1).astype(numpy.float32)
-	lip_motion_points = forward_retarget_lip(lip_motion_points)	* numpy.abs(face_editor_lip_open_ratio)
+	lip_motion_points = forward_retarget_lip(lip_motion_points) * numpy.abs(face_editor_lip_open_ratio)
 	lip_motion_points = lip_motion_points.reshape(-1, 21, 3)
 	return lip_motion_points
 

facefusion/processors/modules/face_enhancer.py

@@ -1,4 +1,5 @@
 from argparse import ArgumentParser
+from functools import lru_cache
 from typing import List
 
 import cv2
@@ -7,251 +8,256 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
-from facefusion.common_helper import create_int_metavar
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, wording
+from facefusion.common_helper import create_float_metavar, create_int_metavar
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_analyser import get_many_faces, get_one_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_static_box_mask
+from facefusion.face_masker import create_box_mask, create_occlusion_mask
 from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
 from facefusion.face_store import get_reference_faces
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FaceEnhancerInputs
+from facefusion.processors.types import FaceEnhancerInputs, FaceEnhancerWeight
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
 from facefusion.vision import read_image, read_static_image, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'codeformer':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'codeformer':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/codeformer.hash',
-				'path': resolve_relative_path('../.assets/models/codeformer.hash')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'codeformer.hash'),
+					'path': resolve_relative_path('../.assets/models/codeformer.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'codeformer.onnx'),
+					'path': resolve_relative_path('../.assets/models/codeformer.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (512, 512)
 		},
-		'sources':
+		'gfpgan_1.2':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/codeformer.onnx',
-				'path': resolve_relative_path('../.assets/models/codeformer.onnx')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gfpgan_1.2.hash'),
+					'path': resolve_relative_path('../.assets/models/gfpgan_1.2.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gfpgan_1.2.onnx'),
+					'path': resolve_relative_path('../.assets/models/gfpgan_1.2.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (512, 512)
 		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
-	},
-	'gfpgan_1.2':
-	{
-		'hashes':
+		'gfpgan_1.3':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gfpgan_1.2.hash',
-				'path': resolve_relative_path('../.assets/models/gfpgan_1.2.hash')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gfpgan_1.3.hash'),
+					'path': resolve_relative_path('../.assets/models/gfpgan_1.3.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gfpgan_1.3.onnx'),
+					'path': resolve_relative_path('../.assets/models/gfpgan_1.3.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (512, 512)
 		},
-		'sources':
+		'gfpgan_1.4':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gfpgan_1.2.onnx',
-				'path': resolve_relative_path('../.assets/models/gfpgan_1.2.onnx')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gfpgan_1.4.hash'),
+					'path': resolve_relative_path('../.assets/models/gfpgan_1.4.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gfpgan_1.4.onnx'),
+					'path': resolve_relative_path('../.assets/models/gfpgan_1.4.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (512, 512)
 		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
-	},
-	'gfpgan_1.3':
-	{
-		'hashes':
+		'gpen_bfr_256':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gfpgan_1.3.hash',
-				'path': resolve_relative_path('../.assets/models/gfpgan_1.3.hash')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_256.hash'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_256.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_256.onnx')
+				}
+			},
+			'template': 'arcface_128',
+			'size': (256, 256)
 		},
-		'sources':
+		'gpen_bfr_512':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gfpgan_1.3.onnx',
-				'path': resolve_relative_path('../.assets/models/gfpgan_1.3.onnx')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_512.hash'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_512.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_512.onnx'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_512.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (512, 512)
 		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
-	},
-	'gfpgan_1.4':
-	{
-		'hashes':
+		'gpen_bfr_1024':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gfpgan_1.4.hash',
-				'path': resolve_relative_path('../.assets/models/gfpgan_1.4.hash')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_1024.hash'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_1024.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_1024.onnx'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_1024.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (1024, 1024)
 		},
-		'sources':
+		'gpen_bfr_2048':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gfpgan_1.4.onnx',
-				'path': resolve_relative_path('../.assets/models/gfpgan_1.4.onnx')
-			}
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_2048.hash'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_2048.hash')
+				}
+			},
+			'sources':
+			{
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'gpen_bfr_2048.onnx'),
+					'path': resolve_relative_path('../.assets/models/gpen_bfr_2048.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (2048, 2048)
 		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
-	},
-	'gpen_bfr_256':
-	{
-		'hashes':
+		'restoreformer_plus_plus':
 		{
-			'face_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_256.hash',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_256.hash')
-			}
-		},
-		'sources':
-		{
-			'face_enhancer':
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'restoreformer_plus_plus.hash'),
+					'path': resolve_relative_path('../.assets/models/restoreformer_plus_plus.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_256.onnx',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_256.onnx')
-			}
-		},
-		'template': 'arcface_128_v2',
-		'size': (256, 256)
-	},
-	'gpen_bfr_512':
-	{
-		'hashes':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_512.hash',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_512.hash')
-			}
-		},
-		'sources':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_512.onnx',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_512.onnx')
-			}
-		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
-	},
-	'gpen_bfr_1024':
-	{
-		'hashes':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_1024.hash',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_1024.hash')
-			}
-		},
-		'sources':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_1024.onnx',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_1024.onnx')
-			}
-		},
-		'template': 'ffhq_512',
-		'size': (1024, 1024)
-	},
-	'gpen_bfr_2048':
-	{
-		'hashes':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_2048.hash',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_2048.hash')
-			}
-		},
-		'sources':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/gpen_bfr_2048.onnx',
-				'path': resolve_relative_path('../.assets/models/gpen_bfr_2048.onnx')
-			}
-		},
-		'template': 'ffhq_512',
-		'size': (2048, 2048)
-	},
-	'restoreformer_plus_plus':
-	{
-		'hashes':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/restoreformer_plus_plus.hash',
-				'path': resolve_relative_path('../.assets/models/restoreformer_plus_plus.hash')
-			}
-		},
-		'sources':
-		{
-			'face_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/restoreformer_plus_plus.onnx',
-				'path': resolve_relative_path('../.assets/models/restoreformer_plus_plus.onnx')
-			}
-		},
-		'template': 'ffhq_512',
-		'size': (512, 512)
+				'face_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'restoreformer_plus_plus.onnx'),
+					'path': resolve_relative_path('../.assets/models/restoreformer_plus_plus.onnx')
+				}
+			},
+			'template': 'ffhq_512',
+			'size': (512, 512)
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('face_enhancer_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('face_enhancer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('face_enhancer_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ state_manager.get_item('face_enhancer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	face_enhancer_model = state_manager.get_item('face_enhancer_model')
-	return MODEL_SET.get(face_enhancer_model)
+	model_name = state_manager.get_item('face_enhancer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-enhancer-model', help = wording.get('help.face_enhancer_model'), default = config.get_str_value('processors.face_enhancer_model', 'gfpgan_1.4'), choices = processors_choices.face_enhancer_models)
-		group_processors.add_argument('--face-enhancer-blend', help = wording.get('help.face_enhancer_blend'), type = int, default = config.get_int_value('processors.face_enhancer_blend', '80'), choices = processors_choices.face_enhancer_blend_range, metavar = create_int_metavar(processors_choices.face_enhancer_blend_range))
-		facefusion.jobs.job_store.register_step_keys([ 'face_enhancer_model', 'face_enhancer_blend' ])
+		group_processors.add_argument('--face-enhancer-model', help = wording.get('help.face_enhancer_model'), default = config.get_str_value('processors', 'face_enhancer_model', 'gfpgan_1.4'), choices = processors_choices.face_enhancer_models)
+		group_processors.add_argument('--face-enhancer-blend', help = wording.get('help.face_enhancer_blend'), type = int, default = config.get_int_value('processors', 'face_enhancer_blend', '80'), choices = processors_choices.face_enhancer_blend_range, metavar = create_int_metavar(processors_choices.face_enhancer_blend_range))
+		group_processors.add_argument('--face-enhancer-weight', help = wording.get('help.face_enhancer_weight'), type = float, default = config.get_float_value('processors', 'face_enhancer_weight', '1.0'), choices = processors_choices.face_enhancer_weight_range, metavar = create_float_metavar(processors_choices.face_enhancer_weight_range))
+		facefusion.jobs.job_store.register_step_keys([ 'face_enhancer_model', 'face_enhancer_blend', 'face_enhancer_weight' ])
 
 
 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('face_enhancer_model', args.get('face_enhancer_model'))
 	apply_state_item('face_enhancer_blend', args.get('face_enhancer_blend'))
+	apply_state_item('face_enhancer_weight', args.get('face_enhancer_weight'))
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -261,7 +267,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -269,6 +275,7 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -284,7 +291,7 @@ def enhance_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionF
 	model_template = get_model_options().get('template')
 	model_size = get_model_options().get('size')
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), model_template, model_size)
-	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
+	box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), (0, 0, 0, 0))
 	crop_masks =\
 	[
 		box_mask
@@ -295,7 +302,8 @@ def enhance_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionF
 		crop_masks.append(occlusion_mask)
 
 	crop_vision_frame = prepare_crop_frame(crop_vision_frame)
-	crop_vision_frame = forward(crop_vision_frame)
+	face_enhancer_weight = numpy.array([ state_manager.get_item('face_enhancer_weight') ]).astype(numpy.double)
+	crop_vision_frame = forward(crop_vision_frame, face_enhancer_weight)
 	crop_vision_frame = normalize_crop_frame(crop_vision_frame)
 	crop_mask = numpy.minimum.reduce(crop_masks).clip(0, 1)
 	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
@@ -303,7 +311,7 @@ def enhance_face(target_face : Face, temp_vision_frame : VisionFrame) -> VisionF
 	return temp_vision_frame
 
 
-def forward(crop_vision_frame : VisionFrame) -> VisionFrame:
+def forward(crop_vision_frame : VisionFrame, face_enhancer_weight : FaceEnhancerWeight) -> VisionFrame:
 	face_enhancer = get_inference_pool().get('face_enhancer')
 	face_enhancer_inputs = {}
 
@@ -311,8 +319,7 @@ def forward(crop_vision_frame : VisionFrame) -> VisionFrame:
 		if face_enhancer_input.name == 'input':
 			face_enhancer_inputs[face_enhancer_input.name] = crop_vision_frame
 		if face_enhancer_input.name == 'weight':
-			weight = numpy.array([ 1 ]).astype(numpy.double)
-			face_enhancer_inputs[face_enhancer_input.name] = weight
+			face_enhancer_inputs[face_enhancer_input.name] = face_enhancer_weight
 
 	with thread_semaphore():
 		crop_vision_frame = face_enhancer.run(None, face_enhancer_inputs)[0][0]
@@ -320,6 +327,16 @@ def forward(crop_vision_frame : VisionFrame) -> VisionFrame:
 	return crop_vision_frame
 
 
+def has_weight_input() -> bool:
+	face_enhancer = get_inference_pool().get('face_enhancer')
+
+	for deep_swapper_input in face_enhancer.get_inputs():
+		if deep_swapper_input.name == 'weight':
+			return True
+
+	return False
+
+
 def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 	crop_vision_frame = crop_vision_frame[:, :, ::-1] / 255.0
 	crop_vision_frame = (crop_vision_frame - 0.5) / 0.5

facefusion/processors/modules/face_swapper.py

@@ -1,324 +1,445 @@
 from argparse import ArgumentParser
+from functools import lru_cache
 from typing import List, Tuple
 
+import cv2
 import numpy
 
+import facefusion.choices
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, wording
 from facefusion.common_helper import get_first
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.execution import has_execution_provider
 from facefusion.face_analyser import get_average_face, get_many_faces, get_one_face
 from facefusion.face_helper import paste_back, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_occlusion_mask, create_region_mask, create_static_box_mask
-from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask, create_region_mask
+from facefusion.face_selector import find_similar_faces, sort_and_filter_faces, sort_faces_by_order
 from facefusion.face_store import get_reference_faces
 from facefusion.filesystem import filter_image_paths, has_image, in_directory, is_image, is_video, resolve_relative_path, same_file_extension
-from facefusion.inference_manager import get_static_model_initializer
+from facefusion.model_helper import get_static_model_initializer
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.pixel_boost import explode_pixel_boost, implode_pixel_boost
-from facefusion.processors.typing import FaceSwapperInputs
-from facefusion.program_helper import find_argument_group, suggest_face_swapper_pixel_boost_choices
+from facefusion.processors.types import FaceSwapperInputs
+from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, Embedding, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Embedding, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
 from facefusion.vision import read_image, read_static_image, read_static_images, unpack_resolution, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'blendswap_256':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'blendswap_256':
 		{
-			'face_swapper':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/blendswap_256.hash',
-				'path': resolve_relative_path('../.assets/models/blendswap_256.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/blendswap_256.onnx',
-				'path': resolve_relative_path('../.assets/models/blendswap_256.onnx')
-			}
-		},
-		'type': 'blendswap',
-		'template': 'ffhq_512',
-		'size': (256, 256),
-		'mean': [ 0.0, 0.0, 0.0 ],
-		'standard_deviation': [ 1.0, 1.0, 1.0 ]
-	},
-	'ghost_1_256':
-	{
-		'hashes':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ghost_1_256.hash',
-				'path': resolve_relative_path('../.assets/models/ghost_1_256.hash')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'blendswap_256.hash'),
+					'path': resolve_relative_path('../.assets/models/blendswap_256.hash')
+				}
 			},
-			'embedding_converter':
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_ghost.hash',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ghost_1_256.onnx',
-				'path': resolve_relative_path('../.assets/models/ghost_1_256.onnx')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'blendswap_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/blendswap_256.onnx')
+				}
 			},
-			'embedding_converter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_ghost.onnx',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
-			}
+			'type': 'blendswap',
+			'template': 'ffhq_512',
+			'size': (256, 256),
+			'mean': [ 0.0, 0.0, 0.0 ],
+			'standard_deviation': [ 1.0, 1.0, 1.0 ]
 		},
-		'type': 'ghost',
-		'template': 'arcface_112_v1',
-		'size': (256, 256),
-		'mean': [ 0.5, 0.5, 0.5 ],
-		'standard_deviation': [ 0.5, 0.5, 0.5 ]
-	},
-	'ghost_2_256':
-	{
-		'hashes':
+		'ghost_1_256':
 		{
-			'face_swapper':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ghost_2_256.hash',
-				'path': resolve_relative_path('../.assets/models/ghost_2_256.hash')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ghost_1_256.hash'),
+					'path': resolve_relative_path('../.assets/models/ghost_1_256.hash')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.hash'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
+				}
 			},
-			'embedding_converter':
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_ghost.hash',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ghost_2_256.onnx',
-				'path': resolve_relative_path('../.assets/models/ghost_2_256.onnx')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ghost_1_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/ghost_1_256.onnx')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.onnx'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
+				}
 			},
-			'embedding_converter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_ghost.onnx',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
-			}
+			'type': 'ghost',
+			'template': 'arcface_112_v1',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		},
-		'type': 'ghost',
-		'template': 'arcface_112_v1',
-		'size': (256, 256),
-		'mean': [ 0.5, 0.5, 0.5 ],
-		'standard_deviation': [ 0.5, 0.5, 0.5 ]
-	},
-	'ghost_3_256':
-	{
-		'hashes':
+		'ghost_2_256':
 		{
-			'face_swapper':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ghost_3_256.hash',
-				'path': resolve_relative_path('../.assets/models/ghost_3_256.hash')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ghost_2_256.hash'),
+					'path': resolve_relative_path('../.assets/models/ghost_2_256.hash')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.hash'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
+				}
 			},
-			'embedding_converter':
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_ghost.hash',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ghost_3_256.onnx',
-				'path': resolve_relative_path('../.assets/models/ghost_3_256.onnx')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ghost_2_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/ghost_2_256.onnx')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.onnx'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
+				}
 			},
-			'embedding_converter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_ghost.onnx',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
-			}
+			'type': 'ghost',
+			'template': 'arcface_112_v1',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		},
-		'type': 'ghost',
-		'template': 'arcface_112_v1',
-		'size': (256, 256),
-		'mean': [ 0.5, 0.5, 0.5 ],
-		'standard_deviation': [ 0.5, 0.5, 0.5 ]
-	},
-	'inswapper_128':
-	{
-		'hashes':
+		'ghost_3_256':
 		{
-			'face_swapper':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/inswapper_128.hash',
-				'path': resolve_relative_path('../.assets/models/inswapper_128.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/inswapper_128.onnx',
-				'path': resolve_relative_path('../.assets/models/inswapper_128.onnx')
-			}
-		},
-		'type': 'inswapper',
-		'template': 'arcface_128_v2',
-		'size': (128, 128),
-		'mean': [ 0.0, 0.0, 0.0 ],
-		'standard_deviation': [ 1.0, 1.0, 1.0 ]
-	},
-	'inswapper_128_fp16':
-	{
-		'hashes':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/inswapper_128_fp16.hash',
-				'path': resolve_relative_path('../.assets/models/inswapper_128_fp16.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/inswapper_128_fp16.onnx',
-				'path': resolve_relative_path('../.assets/models/inswapper_128_fp16.onnx')
-			}
-		},
-		'type': 'inswapper',
-		'template': 'arcface_128_v2',
-		'size': (128, 128),
-		'mean': [ 0.0, 0.0, 0.0 ],
-		'standard_deviation': [ 1.0, 1.0, 1.0 ]
-	},
-	'simswap_256':
-	{
-		'hashes':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/simswap_256.hash',
-				'path': resolve_relative_path('../.assets/models/simswap_256.hash')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ghost_3_256.hash'),
+					'path': resolve_relative_path('../.assets/models/ghost_3_256.hash')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.hash'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.hash')
+				}
 			},
-			'embedding_converter':
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_simswap.hash',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/simswap_256.onnx',
-				'path': resolve_relative_path('../.assets/models/simswap_256.onnx')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ghost_3_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/ghost_3_256.onnx')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_ghost.onnx'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_ghost.onnx')
+				}
 			},
-			'embedding_converter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_simswap.onnx',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.onnx')
-			}
+			'type': 'ghost',
+			'template': 'arcface_112_v1',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		},
-		'type': 'simswap',
-		'template': 'arcface_112_v1',
-		'size': (256, 256),
-		'mean': [ 0.485, 0.456, 0.406 ],
-		'standard_deviation': [ 0.229, 0.224, 0.225 ]
-	},
-	'simswap_unofficial_512':
-	{
-		'hashes':
+		'hififace_unofficial_256':
 		{
-			'face_swapper':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/simswap_unofficial_512.hash',
-				'path': resolve_relative_path('../.assets/models/simswap_unofficial_512.hash')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.1.0', 'hififace_unofficial_256.hash'),
+					'path': resolve_relative_path('../.assets/models/hififace_unofficial_256.hash')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.1.0', 'arcface_converter_hififace.hash'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_hififace.hash')
+				}
 			},
-			'embedding_converter':
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_simswap.hash',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.hash')
-			}
-		},
-		'sources':
-		{
-			'face_swapper':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/simswap_unofficial_512.onnx',
-				'path': resolve_relative_path('../.assets/models/simswap_unofficial_512.onnx')
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.1.0', 'hififace_unofficial_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/hififace_unofficial_256.onnx')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.1.0', 'arcface_converter_hififace.onnx'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_hififace.onnx')
+				}
 			},
-			'embedding_converter':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/arcface_converter_simswap.onnx',
-				'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.onnx')
-			}
+			'type': 'hififace',
+			'template': 'mtcnn_512',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		},
-		'type': 'simswap',
-		'template': 'arcface_112_v1',
-		'size': (512, 512),
-		'mean': [ 0.0, 0.0, 0.0 ],
-		'standard_deviation': [ 1.0, 1.0, 1.0 ]
-	},
-	'uniface_256':
-	{
-		'hashes':
+		'hyperswap_1a_256':
 		{
-			'face_swapper':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/uniface_256.hash',
-				'path': resolve_relative_path('../.assets/models/uniface_256.hash')
-			}
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1a_256.hash'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1a_256.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1a_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1a_256.onnx')
+				}
+			},
+			'type': 'hyperswap',
+			'template': 'arcface_128',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		},
-		'sources':
+		'hyperswap_1b_256':
 		{
-			'face_swapper':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/uniface_256.onnx',
-				'path': resolve_relative_path('../.assets/models/uniface_256.onnx')
-			}
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1b_256.hash'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1b_256.hash')
+				}
+			},
+			'sources':
+				{
+					'face_swapper':
+					{
+						'url': resolve_download_url('models-3.3.0', 'hyperswap_1b_256.onnx'),
+						'path': resolve_relative_path('../.assets/models/hyperswap_1b_256.onnx')
+					}
+				},
+			'type': 'hyperswap',
+			'template': 'arcface_128',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
 		},
-		'type': 'uniface',
-		'template': 'ffhq_512',
-		'size': (256, 256),
-		'mean': [ 0.5, 0.5, 0.5 ],
-		'standard_deviation': [ 0.5, 0.5, 0.5 ]
+		'hyperswap_1c_256':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1c_256.hash'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1c_256.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.3.0', 'hyperswap_1c_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/hyperswap_1c_256.onnx')
+				}
+			},
+			'type': 'hyperswap',
+			'template': 'arcface_128',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
+		},
+		'inswapper_128':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'inswapper_128.hash'),
+					'path': resolve_relative_path('../.assets/models/inswapper_128.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'inswapper_128.onnx'),
+					'path': resolve_relative_path('../.assets/models/inswapper_128.onnx')
+				}
+			},
+			'type': 'inswapper',
+			'template': 'arcface_128',
+			'size': (128, 128),
+			'mean': [ 0.0, 0.0, 0.0 ],
+			'standard_deviation': [ 1.0, 1.0, 1.0 ]
+		},
+		'inswapper_128_fp16':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'inswapper_128_fp16.hash'),
+					'path': resolve_relative_path('../.assets/models/inswapper_128_fp16.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'inswapper_128_fp16.onnx'),
+					'path': resolve_relative_path('../.assets/models/inswapper_128_fp16.onnx')
+				}
+			},
+			'type': 'inswapper',
+			'template': 'arcface_128',
+			'size': (128, 128),
+			'mean': [ 0.0, 0.0, 0.0 ],
+			'standard_deviation': [ 1.0, 1.0, 1.0 ]
+		},
+		'simswap_256':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'simswap_256.hash'),
+					'path': resolve_relative_path('../.assets/models/simswap_256.hash')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.hash'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'simswap_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/simswap_256.onnx')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.onnx'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.onnx')
+				}
+			},
+			'type': 'simswap',
+			'template': 'arcface_112_v1',
+			'size': (256, 256),
+			'mean': [ 0.485, 0.456, 0.406 ],
+			'standard_deviation': [ 0.229, 0.224, 0.225 ]
+		},
+		'simswap_unofficial_512':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'simswap_unofficial_512.hash'),
+					'path': resolve_relative_path('../.assets/models/simswap_unofficial_512.hash')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.hash'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'simswap_unofficial_512.onnx'),
+					'path': resolve_relative_path('../.assets/models/simswap_unofficial_512.onnx')
+				},
+				'embedding_converter':
+				{
+					'url': resolve_download_url('models-3.0.0', 'arcface_converter_simswap.onnx'),
+					'path': resolve_relative_path('../.assets/models/arcface_converter_simswap.onnx')
+				}
+			},
+			'type': 'simswap',
+			'template': 'arcface_112_v1',
+			'size': (512, 512),
+			'mean': [ 0.0, 0.0, 0.0 ],
+			'standard_deviation': [ 1.0, 1.0, 1.0 ]
+		},
+		'uniface_256':
+		{
+			'hashes':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'uniface_256.hash'),
+					'path': resolve_relative_path('../.assets/models/uniface_256.hash')
+				}
+			},
+			'sources':
+			{
+				'face_swapper':
+				{
+					'url': resolve_download_url('models-3.0.0', 'uniface_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/uniface_256.onnx')
+				}
+			},
+			'type': 'uniface',
+			'template': 'ffhq_512',
+			'size': (256, 256),
+			'mean': [ 0.5, 0.5, 0.5 ],
+			'standard_deviation': [ 0.5, 0.5, 0.5 ]
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('face_swapper_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ get_model_name() ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('face_swapper_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ get_model_name() ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	face_swapper_model = state_manager.get_item('face_swapper_model')
-	face_swapper_model = 'inswapper_128' if has_execution_provider('coreml') and face_swapper_model == 'inswapper_128_fp16' else face_swapper_model
-	return MODEL_SET.get(face_swapper_model)
+	model_name = get_model_name()
+	return create_static_model_set('full').get(model_name)
+
+
+def get_model_name() -> str:
+	model_name = state_manager.get_item('face_swapper_model')
+
+	if has_execution_provider('coreml') and model_name == 'inswapper_128_fp16':
+		return 'inswapper_128'
+	return model_name
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--face-swapper-model', help = wording.get('help.face_swapper_model'), default = config.get_str_value('processors.face_swapper_model', 'inswapper_128_fp16'), choices = processors_choices.face_swapper_set.keys())
-		face_swapper_pixel_boost_choices = suggest_face_swapper_pixel_boost_choices(program)
-		group_processors.add_argument('--face-swapper-pixel-boost', help = wording.get('help.face_swapper_pixel_boost'), default = config.get_str_value('processors.face_swapper_pixel_boost', get_first(face_swapper_pixel_boost_choices)), choices = face_swapper_pixel_boost_choices)
+		group_processors.add_argument('--face-swapper-model', help = wording.get('help.face_swapper_model'), default = config.get_str_value('processors', 'face_swapper_model', 'inswapper_128_fp16'), choices = processors_choices.face_swapper_models)
+		known_args, _ = program.parse_known_args()
+		face_swapper_pixel_boost_choices = processors_choices.face_swapper_set.get(known_args.face_swapper_model)
+		group_processors.add_argument('--face-swapper-pixel-boost', help = wording.get('help.face_swapper_pixel_boost'), default = config.get_str_value('processors', 'face_swapper_pixel_boost', get_first(face_swapper_pixel_boost_choices)), choices = face_swapper_pixel_boost_choices)
 		facefusion.jobs.job_store.register_step_keys([ 'face_swapper_model', 'face_swapper_pixel_boost' ])
 
 
@@ -328,11 +449,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -351,7 +471,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -359,9 +479,10 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
-		clear_inference_pool()
 		get_static_model_initializer.cache_clear()
+		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
 		content_analyser.clear_inference_pool()
 		face_classifier.clear_inference_pool()
@@ -381,7 +502,7 @@ def swap_face(source_face : Face, target_face : Face, temp_vision_frame : Vision
 	crop_masks = []
 
 	if 'box' in state_manager.get_item('face_mask_types'):
-		box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
+		box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
 		crop_masks.append(box_mask)
 
 	if 'occlusion' in state_manager.get_item('face_mask_types'):
@@ -396,6 +517,11 @@ def swap_face(source_face : Face, target_face : Face, temp_vision_frame : Vision
 		temp_vision_frames.append(pixel_boost_vision_frame)
 	crop_vision_frame = explode_pixel_boost(temp_vision_frames, pixel_boost_total, model_size, pixel_boost_size)
 
+	if 'area' in state_manager.get_item('face_mask_types'):
+		face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		area_mask = create_area_mask(crop_vision_frame, face_landmark_68, state_manager.get_item('face_mask_areas'))
+		crop_masks.append(area_mask)
+
 	if 'region' in state_manager.get_item('face_mask_types'):
 		region_mask = create_region_mask(crop_vision_frame, state_manager.get_item('face_mask_regions'))
 		crop_masks.append(region_mask)
@@ -410,9 +536,12 @@ def forward_swap_face(source_face : Face, crop_vision_frame : VisionFrame) -> Vi
 	model_type = get_model_options().get('type')
 	face_swapper_inputs = {}
 
+	if has_execution_provider('coreml') and model_type in [ 'ghost', 'uniface' ]:
+		face_swapper.set_providers([ facefusion.choices.execution_provider_set.get('cpu') ])
+
 	for face_swapper_input in face_swapper.get_inputs():
 		if face_swapper_input.name == 'source':
-			if model_type == 'blendswap' or model_type == 'uniface':
+			if model_type in [ 'blendswap', 'uniface' ]:
 				face_swapper_inputs[face_swapper_input.name] = prepare_source_frame(source_face)
 			else:
 				face_swapper_inputs[face_swapper_input.name] = prepare_source_embedding(source_face)
@@ -457,14 +586,21 @@ def prepare_source_embedding(source_face : Face) -> Embedding:
 	if model_type == 'ghost':
 		source_embedding, _ = convert_embedding(source_face)
 		source_embedding = source_embedding.reshape(1, -1)
-	elif model_type == 'inswapper':
+		return source_embedding
+
+	if model_type == 'hyperswap':
+		source_embedding = source_face.normed_embedding.reshape((1, -1))
+		return source_embedding
+
+	if model_type == 'inswapper':
 		model_path = get_model_options().get('sources').get('face_swapper').get('path')
 		model_initializer = get_static_model_initializer(model_path)
 		source_embedding = source_face.embedding.reshape((1, -1))
 		source_embedding = numpy.dot(source_embedding, model_initializer) / numpy.linalg.norm(source_embedding)
-	else:
-		_, source_normed_embedding = convert_embedding(source_face)
-		source_embedding = source_normed_embedding.reshape(1, -1)
+		return source_embedding
+
+	_, source_normed_embedding = convert_embedding(source_face)
+	source_embedding = source_normed_embedding.reshape(1, -1)
 	return source_embedding
 
 
@@ -493,7 +629,7 @@ def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
 	model_standard_deviation = get_model_options().get('standard_deviation')
 
 	crop_vision_frame = crop_vision_frame.transpose(1, 2, 0)
-	if model_type == 'ghost' or model_type == 'uniface':
+	if model_type in [ 'ghost', 'hififace', 'hyperswap', 'uniface' ]:
 		crop_vision_frame = crop_vision_frame * model_standard_deviation + model_mean
 	crop_vision_frame = crop_vision_frame.clip(0, 1)
 	crop_vision_frame = crop_vision_frame[:, :, ::-1] * 255
@@ -529,7 +665,13 @@ def process_frame(inputs : FaceSwapperInputs) -> VisionFrame:
 def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload], update_progress : UpdateProgress) -> None:
 	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
 	source_frames = read_static_images(source_paths)
-	source_faces = get_many_faces(source_frames)
+	source_faces = []
+
+	for source_frame in source_frames:
+		temp_faces = get_many_faces([ source_frame ])
+		temp_faces = sort_faces_by_order(temp_faces, 'large-small')
+		if temp_faces:
+			source_faces.append(get_first(temp_faces))
 	source_face = get_average_face(source_faces)
 
 	for queue_payload in process_manager.manage(queue_payloads):
@@ -548,7 +690,13 @@ def process_frames(source_paths : List[str], queue_payloads : List[QueuePayload]
 def process_image(source_paths : List[str], target_path : str, output_path : str) -> None:
 	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
 	source_frames = read_static_images(source_paths)
-	source_faces = get_many_faces(source_frames)
+	source_faces = []
+
+	for source_frame in source_frames:
+		temp_faces = get_many_faces([ source_frame ])
+		temp_faces = sort_faces_by_order(temp_faces, 'large-small')
+		if temp_faces:
+			source_faces.append(get_first(temp_faces))
 	source_face = get_average_face(source_faces)
 	target_vision_frame = read_static_image(target_path)
 	output_vision_frame = process_frame(

facefusion/processors/modules/frame_colorizer.py

@@ -1,4 +1,5 @@
 from argparse import ArgumentParser
+from functools import lru_cache
 from typing import List
 
 import cv2
@@ -7,144 +8,155 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, inference_manager, logger, process_manager, state_manager, video_manager, wording
 from facefusion.common_helper import create_int_metavar
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
+from facefusion.execution import has_execution_provider
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FrameColorizerInputs
+from facefusion.processors.types import FrameColorizerInputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.types import ApplyStateItem, Args, DownloadScope, ExecutionProvider, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
 from facefusion.vision import read_image, read_static_image, unpack_resolution, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'ddcolor':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'ddcolor':
 		{
-			'frame_colorizer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ddcolor.hash',
-				'path': resolve_relative_path('../.assets/models/ddcolor.hash')
-			}
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ddcolor.hash'),
+					'path': resolve_relative_path('../.assets/models/ddcolor.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ddcolor.onnx'),
+					'path': resolve_relative_path('../.assets/models/ddcolor.onnx')
+				}
+			},
+			'type': 'ddcolor'
 		},
-		'sources':
+		'ddcolor_artistic':
 		{
-			'frame_colorizer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ddcolor.onnx',
-				'path': resolve_relative_path('../.assets/models/ddcolor.onnx')
-			}
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ddcolor_artistic.hash'),
+					'path': resolve_relative_path('../.assets/models/ddcolor_artistic.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ddcolor_artistic.onnx'),
+					'path': resolve_relative_path('../.assets/models/ddcolor_artistic.onnx')
+				}
+			},
+			'type': 'ddcolor'
 		},
-		'type': 'ddcolor'
-	},
-	'ddcolor_artistic':
-	{
-		'hashes':
+		'deoldify':
 		{
-			'frame_colorizer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ddcolor_artistic.hash',
-				'path': resolve_relative_path('../.assets/models/ddcolor_artistic.hash')
-			}
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'deoldify.hash'),
+					'path': resolve_relative_path('../.assets/models/deoldify.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'deoldify.onnx'),
+					'path': resolve_relative_path('../.assets/models/deoldify.onnx')
+				}
+			},
+			'type': 'deoldify'
 		},
-		'sources':
+		'deoldify_artistic':
 		{
-			'frame_colorizer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ddcolor_artistic.onnx',
-				'path': resolve_relative_path('../.assets/models/ddcolor_artistic.onnx')
-			}
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'deoldify_artistic.hash'),
+					'path': resolve_relative_path('../.assets/models/deoldify_artistic.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'deoldify_artistic.onnx'),
+					'path': resolve_relative_path('../.assets/models/deoldify_artistic.onnx')
+				}
+			},
+			'type': 'deoldify'
 		},
-		'type': 'ddcolor'
-	},
-	'deoldify':
-	{
-		'hashes':
+		'deoldify_stable':
 		{
-			'frame_colorizer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/deoldify.hash',
-				'path': resolve_relative_path('../.assets/models/deoldify.hash')
-			}
-		},
-		'sources':
-		{
-			'frame_colorizer':
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'deoldify_stable.hash'),
+					'path': resolve_relative_path('../.assets/models/deoldify_stable.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/deoldify.onnx',
-				'path': resolve_relative_path('../.assets/models/deoldify.onnx')
-			}
-		},
-		'type': 'deoldify'
-	},
-	'deoldify_artistic':
-	{
-		'hashes':
-		{
-			'frame_colorizer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/deoldify_artistic.hash',
-				'path': resolve_relative_path('../.assets/models/deoldify_artistic.hash')
-			}
-		},
-		'sources':
-		{
-			'frame_colorizer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/deoldify_artistic.onnx',
-				'path': resolve_relative_path('../.assets/models/deoldify_artistic.onnx')
-			}
-		},
-		'type': 'deoldify'
-	},
-	'deoldify_stable':
-	{
-		'hashes':
-		{
-			'frame_colorizer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/deoldify_stable.hash',
-				'path': resolve_relative_path('../.assets/models/deoldify_stable.hash')
-			}
-		},
-		'sources':
-		{
-			'frame_colorizer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/deoldify_stable.onnx',
-				'path': resolve_relative_path('../.assets/models/deoldify_stable.onnx')
-			}
-		},
-		'type': 'deoldify'
+				'frame_colorizer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'deoldify_stable.onnx'),
+					'path': resolve_relative_path('../.assets/models/deoldify_stable.onnx')
+				}
+			},
+			'type': 'deoldify'
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('frame_colorizer_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('frame_colorizer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('frame_colorizer_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ state_manager.get_item('frame_colorizer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
+
+
+def resolve_execution_providers() -> List[ExecutionProvider]:
+	if has_execution_provider('coreml'):
+		return [ 'cpu' ]
+	return state_manager.get_item('execution_providers')
 
 
 def get_model_options() -> ModelOptions:
-	frame_colorizer_model = state_manager.get_item('frame_colorizer_model')
-	return MODEL_SET.get(frame_colorizer_model)
+	model_name = state_manager.get_item('frame_colorizer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--frame-colorizer-model', help = wording.get('help.frame_colorizer_model'), default = config.get_str_value('processors.frame_colorizer_model', 'ddcolor'), choices = processors_choices.frame_colorizer_models)
-		group_processors.add_argument('--frame-colorizer-size', help = wording.get('help.frame_colorizer_size'), type = str, default = config.get_str_value('processors.frame_colorizer_size', '256x256'), choices = processors_choices.frame_colorizer_sizes)
-		group_processors.add_argument('--frame-colorizer-blend', help = wording.get('help.frame_colorizer_blend'), type = int, default = config.get_int_value('processors.frame_colorizer_blend', '100'), choices = processors_choices.frame_colorizer_blend_range, metavar = create_int_metavar(processors_choices.frame_colorizer_blend_range))
+		group_processors.add_argument('--frame-colorizer-model', help = wording.get('help.frame_colorizer_model'), default = config.get_str_value('processors', 'frame_colorizer_model', 'ddcolor'), choices = processors_choices.frame_colorizer_models)
+		group_processors.add_argument('--frame-colorizer-size', help = wording.get('help.frame_colorizer_size'), type = str, default = config.get_str_value('processors', 'frame_colorizer_size', '256x256'), choices = processors_choices.frame_colorizer_sizes)
+		group_processors.add_argument('--frame-colorizer-blend', help = wording.get('help.frame_colorizer_blend'), type = int, default = config.get_int_value('processors', 'frame_colorizer_blend', '100'), choices = processors_choices.frame_colorizer_blend_range, metavar = create_int_metavar(processors_choices.frame_colorizer_blend_range))
 		facefusion.jobs.job_store.register_step_keys([ 'frame_colorizer_model', 'frame_colorizer_blend', 'frame_colorizer_size' ])
 
 
@@ -155,11 +167,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -169,7 +180,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -177,6 +188,7 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':

facefusion/processors/modules/frame_enhancer.py

@@ -1,4 +1,5 @@
 from argparse import ArgumentParser
+from functools import lru_cache
 from typing import List
 
 import cv2
@@ -7,295 +8,439 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, inference_manager, logger, process_manager, state_manager, wording
+from facefusion import config, content_analyser, inference_manager, logger, process_manager, state_manager, video_manager, wording
 from facefusion.common_helper import create_int_metavar
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
+from facefusion.execution import has_execution_provider
 from facefusion.filesystem import in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FrameEnhancerInputs
+from facefusion.processors.types import FrameEnhancerInputs
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.types import ApplyStateItem, Args, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
 from facefusion.vision import create_tile_frames, merge_tile_frames, read_image, read_static_image, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'clear_reality_x4':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'clear_reality_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/clear_reality_x4.hash',
-				'path': resolve_relative_path('../.assets/models/clear_reality_x4.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'clear_reality_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/clear_reality_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'clear_reality_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/clear_reality_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'sources':
+		'lsdir_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/clear_reality_x4.onnx',
-				'path': resolve_relative_path('../.assets/models/clear_reality_x4.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'lsdir_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/lsdir_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'lsdir_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/lsdir_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'size': (128, 8, 4),
-		'scale': 4
-	},
-	'lsdir_x4':
-	{
-		'hashes':
+		'nomos8k_sc_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/lsdir_x4.hash',
-				'path': resolve_relative_path('../.assets/models/lsdir_x4.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'nomos8k_sc_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/nomos8k_sc_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'nomos8k_sc_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/nomos8k_sc_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'sources':
+		'real_esrgan_x2':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/lsdir_x4.onnx',
-				'path': resolve_relative_path('../.assets/models/lsdir_x4.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x2.hash'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x2.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x2.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x2.onnx')
+				}
+			},
+			'size': (256, 16, 8),
+			'scale': 2
 		},
-		'size': (128, 8, 4),
-		'scale': 4
-	},
-	'nomos8k_sc_x4':
-	{
-		'hashes':
+		'real_esrgan_x2_fp16':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/nomos8k_sc_x4.hash',
-				'path': resolve_relative_path('../.assets/models/nomos8k_sc_x4.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x2_fp16.hash'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x2_fp16.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x2_fp16.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x2_fp16.onnx')
+				}
+			},
+			'size': (256, 16, 8),
+			'scale': 2
 		},
-		'sources':
+		'real_esrgan_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/nomos8k_sc_x4.onnx',
-				'path': resolve_relative_path('../.assets/models/nomos8k_sc_x4.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x4.onnx')
+				}
+			},
+			'size': (256, 16, 8),
+			'scale': 4
 		},
-		'size': (128, 8, 4),
-		'scale': 4
-	},
-	'real_esrgan_x2':
-	{
-		'hashes':
+		'real_esrgan_x4_fp16':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x2.hash',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x2.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x4_fp16.hash'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x4_fp16.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x4_fp16.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x4_fp16.onnx')
+				}
+			},
+			'size': (256, 16, 8),
+			'scale': 4
 		},
-		'sources':
+		'real_esrgan_x8':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x2.onnx',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x2.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x8.hash'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x8.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x8.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x8.onnx')
+				}
+			},
+			'size': (256, 16, 8),
+			'scale': 8
 		},
-		'size': (256, 16, 8),
-		'scale': 2
-	},
-	'real_esrgan_x2_fp16':
-	{
-		'hashes':
+		'real_esrgan_x8_fp16':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x2_fp16.hash',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x2_fp16.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x8_fp16.hash'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x8_fp16.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_esrgan_x8_fp16.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_esrgan_x8_fp16.onnx')
+				}
+			},
+			'size': (256, 16, 8),
+			'scale': 8
 		},
-		'sources':
+		'real_hatgan_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x2_fp16.onnx',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x2_fp16.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_hatgan_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/real_hatgan_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'real_hatgan_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_hatgan_x4.onnx')
+				}
+			},
+			'size': (256, 16, 8),
+			'scale': 4
 		},
-		'size': (256, 16, 8),
-		'scale': 2
-	},
-	'real_esrgan_x4':
-	{
-		'hashes':
+		'real_web_photo_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x4.hash',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x4.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'real_web_photo_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/real_web_photo_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'real_web_photo_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/real_web_photo_x4.onnx')
+				}
+			},
+			'size': (64, 4, 2),
+			'scale': 4
 		},
-		'sources':
+		'realistic_rescaler_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x4.onnx',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x4.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'realistic_rescaler_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/realistic_rescaler_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'realistic_rescaler_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/realistic_rescaler_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'size': (256, 16, 8),
-		'scale': 4
-	},
-	'real_esrgan_x4_fp16':
-	{
-		'hashes':
+		'remacri_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x4_fp16.hash',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x4_fp16.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'remacri_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/remacri_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'remacri_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/remacri_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'sources':
+		'siax_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x4_fp16.onnx',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x4_fp16.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'siax_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/siax_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'siax_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/siax_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'size': (256, 16, 8),
-		'scale': 4
-	},
-	'real_esrgan_x8':
-	{
-		'hashes':
+		'span_kendata_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x8.hash',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x8.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'span_kendata_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/span_kendata_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'span_kendata_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/span_kendata_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'sources':
+		'swin2_sr_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x8.onnx',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x8.onnx')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'swin2_sr_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/swin2_sr_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.1.0', 'swin2_sr_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/swin2_sr_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'size': (256, 16, 8),
-		'scale': 8
-	},
-	'real_esrgan_x8_fp16':
-	{
-		'hashes':
+		'ultra_sharp_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x8_fp16.hash',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x8_fp16.hash')
-			}
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ultra_sharp_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/ultra_sharp_x4.hash')
+				}
+			},
+			'sources':
+			{
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'ultra_sharp_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/ultra_sharp_x4.onnx')
+				}
+			},
+			'size': (128, 8, 4),
+			'scale': 4
 		},
-		'sources':
+		'ultra_sharp_2_x4':
 		{
-			'frame_enhancer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_esrgan_x8_fp16.onnx',
-				'path': resolve_relative_path('../.assets/models/real_esrgan_x8_fp16.onnx')
-			}
-		},
-		'size': (256, 16, 8),
-		'scale': 8
-	},
-	'real_hatgan_x4':
-	{
-		'hashes':
-		{
-			'frame_enhancer':
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'ultra_sharp_2_x4.hash'),
+					'path': resolve_relative_path('../.assets/models/ultra_sharp_2_x4.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_hatgan_x4.hash',
-				'path': resolve_relative_path('../.assets/models/real_hatgan_x4.hash')
-			}
-		},
-		'sources':
-		{
-			'frame_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/real_hatgan_x4.onnx',
-				'path': resolve_relative_path('../.assets/models/real_hatgan_x4.onnx')
-			}
-		},
-		'size': (256, 16, 8),
-		'scale': 4
-	},
-	'span_kendata_x4':
-	{
-		'hashes':
-		{
-			'frame_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/span_kendata_x4.hash',
-				'path': resolve_relative_path('../.assets/models/span_kendata_x4.hash')
-			}
-		},
-		'sources':
-		{
-			'frame_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/span_kendata_x4.onnx',
-				'path': resolve_relative_path('../.assets/models/span_kendata_x4.onnx')
-			}
-		},
-		'size': (128, 8, 4),
-		'scale': 4
-	},
-	'ultra_sharp_x4':
-	{
-		'hashes':
-		{
-			'frame_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ultra_sharp_x4.hash',
-				'path': resolve_relative_path('../.assets/models/ultra_sharp_x4.hash')
-			}
-		},
-		'sources':
-		{
-			'frame_enhancer':
-			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/ultra_sharp_x4.onnx',
-				'path': resolve_relative_path('../.assets/models/ultra_sharp_x4.onnx')
-			}
-		},
-		'size': (128, 8, 4),
-		'scale': 4
+				'frame_enhancer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'ultra_sharp_2_x4.onnx'),
+					'path': resolve_relative_path('../.assets/models/ultra_sharp_2_x4.onnx')
+				}
+			},
+			'size': (1024, 64, 32),
+			'scale': 4
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('frame_enhancer_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ get_frame_enhancer_model() ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('frame_enhancer_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ get_frame_enhancer_model() ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
+	model_name = get_frame_enhancer_model()
+	return create_static_model_set('full').get(model_name)
+
+
+def get_frame_enhancer_model() -> str:
 	frame_enhancer_model = state_manager.get_item('frame_enhancer_model')
-	return MODEL_SET.get(frame_enhancer_model)
+
+	if has_execution_provider('coreml'):
+		if frame_enhancer_model == 'real_esrgan_x2_fp16':
+			return 'real_esrgan_x2'
+		if frame_enhancer_model == 'real_esrgan_x4_fp16':
+			return 'real_esrgan_x4'
+		if frame_enhancer_model == 'real_esrgan_x8_fp16':
+			return 'real_esrgan_x8'
+	return frame_enhancer_model
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--frame-enhancer-model', help = wording.get('help.frame_enhancer_model'), default = config.get_str_value('processors.frame_enhancer_model', 'span_kendata_x4'), choices = processors_choices.frame_enhancer_models)
-		group_processors.add_argument('--frame-enhancer-blend', help = wording.get('help.frame_enhancer_blend'), type = int, default = config.get_int_value('processors.frame_enhancer_blend', '80'), choices = processors_choices.frame_enhancer_blend_range, metavar = create_int_metavar(processors_choices.frame_enhancer_blend_range))
+		group_processors.add_argument('--frame-enhancer-model', help = wording.get('help.frame_enhancer_model'), default = config.get_str_value('processors', 'frame_enhancer_model', 'span_kendata_x4'), choices = processors_choices.frame_enhancer_models)
+		group_processors.add_argument('--frame-enhancer-blend', help = wording.get('help.frame_enhancer_blend'), type = int, default = config.get_int_value('processors', 'frame_enhancer_blend', '80'), choices = processors_choices.frame_enhancer_blend_range, metavar = create_int_metavar(processors_choices.frame_enhancer_blend_range))
 		facefusion.jobs.job_store.register_step_keys([ 'frame_enhancer_model', 'frame_enhancer_blend' ])
 
 
@@ -305,11 +450,10 @@ def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -319,7 +463,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -327,6 +471,7 @@ def pre_process(mode : ProcessMode) -> bool:
 
 def post_process() -> None:
 	read_static_image.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -364,7 +509,7 @@ def forward(tile_vision_frame : VisionFrame) -> VisionFrame:
 def prepare_tile_frame(vision_tile_frame : VisionFrame) -> VisionFrame:
 	vision_tile_frame = numpy.expand_dims(vision_tile_frame[:, :, ::-1], axis = 0)
 	vision_tile_frame = vision_tile_frame.transpose(0, 3, 1, 2)
-	vision_tile_frame = vision_tile_frame.astype(numpy.float32) / 255
+	vision_tile_frame = vision_tile_frame.astype(numpy.float32) / 255.0
 	return vision_tile_frame
 
 

facefusion/processors/modules/lip_syncer.py

@@ -1,4 +1,5 @@
 from argparse import ArgumentParser
+from functools import lru_cache
 from typing import List
 
 import cv2
@@ -7,101 +8,130 @@ import numpy
 import facefusion.jobs.job_manager
 import facefusion.jobs.job_store
 import facefusion.processors.core as processors
-from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, voice_extractor, wording
+from facefusion import config, content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, inference_manager, logger, process_manager, state_manager, video_manager, voice_extractor, wording
 from facefusion.audio import create_empty_audio_frame, get_voice_frame, read_static_voice
+from facefusion.common_helper import create_float_metavar
 from facefusion.common_helper import get_first
-from facefusion.download import conditional_download_hashes, conditional_download_sources
+from facefusion.download import conditional_download_hashes, conditional_download_sources, resolve_download_url
 from facefusion.face_analyser import get_many_faces, get_one_face
 from facefusion.face_helper import create_bounding_box, paste_back, warp_face_by_bounding_box, warp_face_by_face_landmark_5
-from facefusion.face_masker import create_mouth_mask, create_occlusion_mask, create_static_box_mask
+from facefusion.face_masker import create_area_mask, create_box_mask, create_occlusion_mask
 from facefusion.face_selector import find_similar_faces, sort_and_filter_faces
 from facefusion.face_store import get_reference_faces
 from facefusion.filesystem import filter_audio_paths, has_audio, in_directory, is_image, is_video, resolve_relative_path, same_file_extension
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import LipSyncerInputs
+from facefusion.processors.types import LipSyncerInputs, LipSyncerWeight
 from facefusion.program_helper import find_argument_group
 from facefusion.thread_helper import conditional_thread_semaphore
-from facefusion.typing import ApplyStateItem, Args, AudioFrame, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
+from facefusion.types import ApplyStateItem, Args, AudioFrame, BoundingBox, DownloadScope, Face, InferencePool, ModelOptions, ModelSet, ProcessMode, QueuePayload, UpdateProgress, VisionFrame
 from facefusion.vision import read_image, read_static_image, restrict_video_fps, write_image
 
-MODEL_SET : ModelSet =\
-{
-	'wav2lip_96':
+
+@lru_cache(maxsize = None)
+def create_static_model_set(download_scope : DownloadScope) -> ModelSet:
+	return\
 	{
-		'hashes':
+		'edtalk_256':
 		{
-			'lip_syncer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/wav2lip_96.hash',
-				'path': resolve_relative_path('../.assets/models/wav2lip_96.hash')
-			}
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'edtalk_256.hash'),
+					'path': resolve_relative_path('../.assets/models/edtalk_256.hash')
+				}
+			},
+			'sources':
+			{
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.3.0', 'edtalk_256.onnx'),
+					'path': resolve_relative_path('../.assets/models/edtalk_256.onnx')
+				}
+			},
+			'type': 'edtalk',
+			'size': (256, 256)
 		},
-		'sources':
+		'wav2lip_96':
 		{
-			'lip_syncer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/wav2lip_96.onnx',
-				'path': resolve_relative_path('../.assets/models/wav2lip_96.onnx')
-			}
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'wav2lip_96.hash'),
+					'path': resolve_relative_path('../.assets/models/wav2lip_96.hash')
+				}
+			},
+			'sources':
+			{
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'wav2lip_96.onnx'),
+					'path': resolve_relative_path('../.assets/models/wav2lip_96.onnx')
+				}
+			},
+			'type': 'wav2lip',
+			'size': (96, 96)
 		},
-		'size': (96, 96)
-	},
-	'wav2lip_gan_96':
-	{
-		'hashes':
+		'wav2lip_gan_96':
 		{
-			'lip_syncer':
+			'hashes':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/wav2lip_gan_96.hash',
-				'path': resolve_relative_path('../.assets/models/wav2lip_gan_96.hash')
-			}
-		},
-		'sources':
-		{
-			'lip_syncer':
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'wav2lip_gan_96.hash'),
+					'path': resolve_relative_path('../.assets/models/wav2lip_gan_96.hash')
+				}
+			},
+			'sources':
 			{
-				'url': 'https://github.com/facefusion/facefusion-assets/releases/download/models-3.0.0/wav2lip_gan_96.onnx',
-				'path': resolve_relative_path('../.assets/models/wav2lip_gan_96.onnx')
-			}
-		},
-		'size': (96, 96)
+				'lip_syncer':
+				{
+					'url': resolve_download_url('models-3.0.0', 'wav2lip_gan_96.onnx'),
+					'path': resolve_relative_path('../.assets/models/wav2lip_gan_96.onnx')
+				}
+			},
+			'type': 'wav2lip',
+			'size': (96, 96)
+		}
 	}
-}
 
 
 def get_inference_pool() -> InferencePool:
-	model_sources = get_model_options().get('sources')
-	model_context = __name__ + '.' + state_manager.get_item('lip_syncer_model')
-	return inference_manager.get_inference_pool(model_context, model_sources)
+	model_names = [ state_manager.get_item('lip_syncer_model') ]
+	model_source_set = get_model_options().get('sources')
+
+	return inference_manager.get_inference_pool(__name__, model_names, model_source_set)
 
 
 def clear_inference_pool() -> None:
-	model_context = __name__ + '.' + state_manager.get_item('lip_syncer_model')
-	inference_manager.clear_inference_pool(model_context)
+	model_names = [ state_manager.get_item('lip_syncer_model') ]
+	inference_manager.clear_inference_pool(__name__, model_names)
 
 
 def get_model_options() -> ModelOptions:
-	lip_syncer_model = state_manager.get_item('lip_syncer_model')
-	return MODEL_SET.get(lip_syncer_model)
+	model_name = state_manager.get_item('lip_syncer_model')
+	return create_static_model_set('full').get(model_name)
 
 
 def register_args(program : ArgumentParser) -> None:
 	group_processors = find_argument_group(program, 'processors')
 	if group_processors:
-		group_processors.add_argument('--lip-syncer-model', help = wording.get('help.lip_syncer_model'), default = config.get_str_value('processors.lip_syncer_model', 'wav2lip_gan_96'), choices = processors_choices.lip_syncer_models)
-		facefusion.jobs.job_store.register_step_keys([ 'lip_syncer_model' ])
+		group_processors.add_argument('--lip-syncer-model', help = wording.get('help.lip_syncer_model'), default = config.get_str_value('processors', 'lip_syncer_model', 'wav2lip_gan_96'), choices = processors_choices.lip_syncer_models)
+		group_processors.add_argument('--lip-syncer-weight', help = wording.get('help.lip_syncer_weight'), type = float, default = config.get_float_value('processors', 'lip_syncer_weight', '0.5'), choices = processors_choices.lip_syncer_weight_range, metavar = create_float_metavar(processors_choices.lip_syncer_weight_range))
+		facefusion.jobs.job_store.register_step_keys([ 'lip_syncer_model', 'lip_syncer_weight' ])
 
 
 def apply_args(args : Args, apply_state_item : ApplyStateItem) -> None:
 	apply_state_item('lip_syncer_model', args.get('lip_syncer_model'))
+	apply_state_item('lip_syncer_weight', args.get('lip_syncer_weight'))
 
 
 def pre_check() -> bool:
-	download_directory_path = resolve_relative_path('../.assets/models')
-	model_hashes = get_model_options().get('hashes')
-	model_sources = get_model_options().get('sources')
+	model_hash_set = get_model_options().get('hashes')
+	model_source_set = get_model_options().get('sources')
 
-	return conditional_download_hashes(download_directory_path, model_hashes) and conditional_download_sources(download_directory_path, model_sources)
+	return conditional_download_hashes(model_hash_set) and conditional_download_sources(model_source_set)
 
 
 def pre_process(mode : ProcessMode) -> bool:
@@ -114,7 +144,7 @@ def pre_process(mode : ProcessMode) -> bool:
 	if mode == 'output' and not in_directory(state_manager.get_item('output_path')):
 		logger.error(wording.get('specify_image_or_video_output') + wording.get('exclamation_mark'), __name__)
 		return False
-	if mode == 'output' and not same_file_extension([ state_manager.get_item('target_path'), state_manager.get_item('output_path') ]):
+	if mode == 'output' and not same_file_extension(state_manager.get_item('target_path'), state_manager.get_item('output_path')):
 		logger.error(wording.get('match_target_and_output_extension') + wording.get('exclamation_mark'), __name__)
 		return False
 	return True
@@ -123,6 +153,7 @@ def pre_process(mode : ProcessMode) -> bool:
 def post_process() -> None:
 	read_static_image.cache_clear()
 	read_static_voice.cache_clear()
+	video_manager.clear_video_pool()
 	if state_manager.get_item('video_memory_strategy') in [ 'strict', 'moderate' ]:
 		clear_inference_pool()
 	if state_manager.get_item('video_memory_strategy') == 'strict':
@@ -136,68 +167,115 @@ def post_process() -> None:
 
 
 def sync_lip(target_face : Face, temp_audio_frame : AudioFrame, temp_vision_frame : VisionFrame) -> VisionFrame:
+	model_type = get_model_options().get('type')
 	model_size = get_model_options().get('size')
 	temp_audio_frame = prepare_audio_frame(temp_audio_frame)
 	crop_vision_frame, affine_matrix = warp_face_by_face_landmark_5(temp_vision_frame, target_face.landmark_set.get('5/68'), 'ffhq_512', (512, 512))
-	face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
-	bounding_box = create_bounding_box(face_landmark_68)
-	bounding_box[1] -= numpy.abs(bounding_box[3] - bounding_box[1]) * 0.125
-	mouth_mask = create_mouth_mask(face_landmark_68)
-	box_mask = create_static_box_mask(crop_vision_frame.shape[:2][::-1], state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
-	crop_masks =\
-	[
-		mouth_mask,
-		box_mask
-	]
+	crop_masks = []
 
 	if 'occlusion' in state_manager.get_item('face_mask_types'):
 		occlusion_mask = create_occlusion_mask(crop_vision_frame)
 		crop_masks.append(occlusion_mask)
 
-	close_vision_frame, close_matrix = warp_face_by_bounding_box(crop_vision_frame, bounding_box, model_size)
-	close_vision_frame = prepare_crop_frame(close_vision_frame)
-	close_vision_frame = forward(temp_audio_frame, close_vision_frame)
-	close_vision_frame = normalize_close_frame(close_vision_frame)
-	crop_vision_frame = cv2.warpAffine(close_vision_frame, cv2.invertAffineTransform(close_matrix), (512, 512), borderMode = cv2.BORDER_REPLICATE)
+	if model_type == 'edtalk':
+		lip_syncer_weight = numpy.array([ state_manager.get_item('lip_syncer_weight') ]).astype(numpy.float32)
+		box_mask = create_box_mask(crop_vision_frame, state_manager.get_item('face_mask_blur'), state_manager.get_item('face_mask_padding'))
+		crop_masks.append(box_mask)
+		crop_vision_frame = prepare_crop_frame(crop_vision_frame)
+		crop_vision_frame = forward_edtalk(temp_audio_frame, crop_vision_frame, lip_syncer_weight)
+		crop_vision_frame = normalize_crop_frame(crop_vision_frame)
+	if model_type == 'wav2lip':
+		face_landmark_68 = cv2.transform(target_face.landmark_set.get('68').reshape(1, -1, 2), affine_matrix).reshape(-1, 2)
+		area_mask = create_area_mask(crop_vision_frame, face_landmark_68, [ 'lower-face' ])
+		crop_masks.append(area_mask)
+		bounding_box = create_bounding_box(face_landmark_68)
+		bounding_box = resize_bounding_box(bounding_box, 1 / 8)
+		area_vision_frame, area_matrix = warp_face_by_bounding_box(crop_vision_frame, bounding_box, model_size)
+		area_vision_frame = prepare_crop_frame(area_vision_frame)
+		area_vision_frame = forward_wav2lip(temp_audio_frame, area_vision_frame)
+		area_vision_frame = normalize_crop_frame(area_vision_frame)
+		crop_vision_frame = cv2.warpAffine(area_vision_frame, cv2.invertAffineTransform(area_matrix), (512, 512), borderMode = cv2.BORDER_REPLICATE)
+
 	crop_mask = numpy.minimum.reduce(crop_masks)
 	paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
 	return paste_vision_frame
 
 
-def forward(temp_audio_frame : AudioFrame, close_vision_frame : VisionFrame) -> VisionFrame:
+def forward_edtalk(temp_audio_frame : AudioFrame, crop_vision_frame : VisionFrame, lip_syncer_weight : LipSyncerWeight) -> VisionFrame:
 	lip_syncer = get_inference_pool().get('lip_syncer')
 
 	with conditional_thread_semaphore():
-		close_vision_frame = lip_syncer.run(None,
+		crop_vision_frame = lip_syncer.run(None,
 		{
 			'source': temp_audio_frame,
-			'target': close_vision_frame
+			'target': crop_vision_frame,
+			'weight': lip_syncer_weight
 		})[0]
 
-	return close_vision_frame
+	return crop_vision_frame
+
+
+def forward_wav2lip(temp_audio_frame : AudioFrame, area_vision_frame : VisionFrame) -> VisionFrame:
+	lip_syncer = get_inference_pool().get('lip_syncer')
+
+	with conditional_thread_semaphore():
+		area_vision_frame = lip_syncer.run(None,
+		{
+			'source': temp_audio_frame,
+			'target': area_vision_frame
+		})[0]
+
+	return area_vision_frame
 
 
 def prepare_audio_frame(temp_audio_frame : AudioFrame) -> AudioFrame:
+	model_type = get_model_options().get('type')
 	temp_audio_frame = numpy.maximum(numpy.exp(-5 * numpy.log(10)), temp_audio_frame)
 	temp_audio_frame = numpy.log10(temp_audio_frame) * 1.6 + 3.2
 	temp_audio_frame = temp_audio_frame.clip(-4, 4).astype(numpy.float32)
+
+	if model_type == 'wav2lip':
+		temp_audio_frame = temp_audio_frame * state_manager.get_item('lip_syncer_weight') * 2.0
+
 	temp_audio_frame = numpy.expand_dims(temp_audio_frame, axis = (0, 1))
 	return temp_audio_frame
 
 
 def prepare_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
-	crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
-	prepare_vision_frame = crop_vision_frame.copy()
-	prepare_vision_frame[:, 48:] = 0
-	crop_vision_frame = numpy.concatenate((prepare_vision_frame, crop_vision_frame), axis = 3)
-	crop_vision_frame = crop_vision_frame.transpose(0, 3, 1, 2).astype('float32') / 255.0
+	model_type = get_model_options().get('type')
+	model_size = get_model_options().get('size')
+
+	if model_type == 'edtalk':
+		crop_vision_frame = cv2.resize(crop_vision_frame, model_size, interpolation = cv2.INTER_AREA)
+		crop_vision_frame = crop_vision_frame[:, :, ::-1] / 255.0
+		crop_vision_frame = numpy.expand_dims(crop_vision_frame.transpose(2, 0, 1), axis = 0).astype(numpy.float32)
+	if model_type == 'wav2lip':
+		crop_vision_frame = numpy.expand_dims(crop_vision_frame, axis = 0)
+		prepare_vision_frame = crop_vision_frame.copy()
+		prepare_vision_frame[:, model_size[0] // 2:] = 0
+		crop_vision_frame = numpy.concatenate((prepare_vision_frame, crop_vision_frame), axis = 3)
+		crop_vision_frame = crop_vision_frame.transpose(0, 3, 1, 2).astype('float32') / 255.0
+
 	return crop_vision_frame
 
 
-def normalize_close_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+def resize_bounding_box(bounding_box : BoundingBox, aspect_ratio : float) -> BoundingBox:
+	x1, y1, x2, y2 = bounding_box
+	y1 -= numpy.abs(y2 - y1) * aspect_ratio
+	bounding_box[1] = max(y1, 0)
+	return bounding_box
+
+
+def normalize_crop_frame(crop_vision_frame : VisionFrame) -> VisionFrame:
+	model_type = get_model_options().get('type')
 	crop_vision_frame = crop_vision_frame[0].transpose(1, 2, 0)
 	crop_vision_frame = crop_vision_frame.clip(0, 1) * 255
 	crop_vision_frame = crop_vision_frame.astype(numpy.uint8)
+
+	if model_type == 'edtalk':
+		crop_vision_frame = crop_vision_frame[:, :, ::-1]
+		crop_vision_frame = cv2.resize(crop_vision_frame, (512, 512), interpolation = cv2.INTER_CUBIC)
+
 	return crop_vision_frame
 
 

facefusion/processors/pixel_boost.py

@@ -3,7 +3,7 @@ from typing import List
 import numpy
 from cv2.typing import Size
 
-from facefusion.typing import VisionFrame
+from facefusion.types import VisionFrame
 
 
 def implode_pixel_boost(crop_vision_frame : VisionFrame, pixel_boost_total : int, model_size : Size) -> VisionFrame:
@@ -13,6 +13,6 @@ def implode_pixel_boost(crop_vision_frame : VisionFrame, pixel_boost_total : int
 
 
 def explode_pixel_boost(temp_vision_frames : List[VisionFrame], pixel_boost_total : int, model_size : Size, pixel_boost_size : Size) -> VisionFrame:
-	crop_vision_frame = numpy.stack(temp_vision_frames, axis = 0).reshape(pixel_boost_total, pixel_boost_total, model_size[0], model_size[1], 3)
+	crop_vision_frame = numpy.stack(temp_vision_frames).reshape(pixel_boost_total, pixel_boost_total, model_size[0], model_size[1], 3)
 	crop_vision_frame = crop_vision_frame.transpose(2, 0, 3, 1, 4).reshape(pixel_boost_size[0], pixel_boost_size[1], 3)
 	return crop_vision_frame

facefusion/processors/types.py

@@ -1,26 +1,32 @@
-from typing import Any, Dict, List, Literal, TypedDict
+from typing import Any, Dict, List, Literal, TypeAlias, TypedDict
 
-from numpy._typing import NDArray
+from numpy.typing import NDArray
 
-from facefusion.typing import AppContext, AudioFrame, Face, FaceSet, VisionFrame
+from facefusion.types import AppContext, AudioFrame, Face, FaceSet, VisionFrame
 
 AgeModifierModel = Literal['styleganex_age']
+DeepSwapperModel : TypeAlias = str
 ExpressionRestorerModel = Literal['live_portrait']
 FaceDebuggerItem = Literal['bounding-box', 'face-landmark-5', 'face-landmark-5/68', 'face-landmark-68', 'face-landmark-68/5', 'face-mask', 'face-detector-score', 'face-landmarker-score', 'age', 'gender', 'race']
 FaceEditorModel = Literal['live_portrait']
 FaceEnhancerModel = Literal['codeformer', 'gfpgan_1.2', 'gfpgan_1.3', 'gfpgan_1.4', 'gpen_bfr_256', 'gpen_bfr_512', 'gpen_bfr_1024', 'gpen_bfr_2048', 'restoreformer_plus_plus']
-FaceSwapperModel = Literal['blendswap_256', 'ghost_1_256', 'ghost_2_256', 'ghost_3_256', 'inswapper_128', 'inswapper_128_fp16', 'simswap_256', 'simswap_unofficial_512', 'uniface_256']
+FaceSwapperModel = Literal['blendswap_256', 'ghost_1_256', 'ghost_2_256', 'ghost_3_256', 'hififace_unofficial_256', 'hyperswap_1a_256', 'hyperswap_1b_256', 'hyperswap_1c_256', 'inswapper_128', 'inswapper_128_fp16', 'simswap_256', 'simswap_unofficial_512', 'uniface_256']
 FrameColorizerModel = Literal['ddcolor', 'ddcolor_artistic', 'deoldify', 'deoldify_artistic', 'deoldify_stable']
-FrameEnhancerModel = Literal['clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_hatgan_x4', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'span_kendata_x4', 'ultra_sharp_x4']
-LipSyncerModel = Literal['wav2lip_96', 'wav2lip_gan_96']
+FrameEnhancerModel = Literal['clear_reality_x4', 'lsdir_x4', 'nomos8k_sc_x4', 'real_esrgan_x2', 'real_esrgan_x2_fp16', 'real_esrgan_x4', 'real_esrgan_x4_fp16', 'real_esrgan_x8', 'real_esrgan_x8_fp16', 'real_hatgan_x4', 'real_web_photo_x4', 'realistic_rescaler_x4', 'remacri_x4', 'siax_x4', 'span_kendata_x4', 'swin2_sr_x4', 'ultra_sharp_x4', 'ultra_sharp_2_x4']
+LipSyncerModel = Literal['edtalk_256', 'wav2lip_96', 'wav2lip_gan_96']
 
-FaceSwapperSet = Dict[FaceSwapperModel, List[str]]
+FaceSwapperSet : TypeAlias = Dict[FaceSwapperModel, List[str]]
 
 AgeModifierInputs = TypedDict('AgeModifierInputs',
 {
 	'reference_faces' : FaceSet,
 	'target_vision_frame' : VisionFrame
 })
+DeepSwapperInputs = TypedDict('DeepSwapperInputs',
+{
+	'reference_faces' : FaceSet,
+	'target_vision_frame' : VisionFrame
+})
 ExpressionRestorerInputs = TypedDict('ExpressionRestorerInputs',
 {
 	'reference_faces' : FaceSet,
@@ -67,6 +73,8 @@ ProcessorStateKey = Literal\
 [
 	'age_modifier_model',
 	'age_modifier_direction',
+	'deep_swapper_model',
+	'deep_swapper_morph',
 	'expression_restorer_model',
 	'expression_restorer_factor',
 	'face_debugger_items',
@@ -87,6 +95,7 @@ ProcessorStateKey = Literal\
 	'face_editor_head_roll',
 	'face_enhancer_model',
 	'face_enhancer_blend',
+	'face_enhancer_weight',
 	'face_swapper_model',
 	'face_swapper_pixel_boost',
 	'frame_colorizer_model',
@@ -94,12 +103,15 @@ ProcessorStateKey = Literal\
 	'frame_colorizer_blend',
 	'frame_enhancer_model',
 	'frame_enhancer_blend',
-	'lip_syncer_model'
+	'lip_syncer_model',
+	'lip_syncer_weight'
 ]
 ProcessorState = TypedDict('ProcessorState',
 {
 	'age_modifier_model' : AgeModifierModel,
 	'age_modifier_direction' : int,
+	'deep_swapper_model' : DeepSwapperModel,
+	'deep_swapper_morph' : int,
 	'expression_restorer_model' : ExpressionRestorerModel,
 	'expression_restorer_factor' : int,
 	'face_debugger_items' : List[FaceDebuggerItem],
@@ -120,6 +132,7 @@ ProcessorState = TypedDict('ProcessorState',
 	'face_editor_head_roll' : float,
 	'face_enhancer_model' : FaceEnhancerModel,
 	'face_enhancer_blend' : int,
+	'face_enhancer_weight' : float,
 	'face_swapper_model' : FaceSwapperModel,
 	'face_swapper_pixel_boost' : str,
 	'frame_colorizer_model' : FrameColorizerModel,
@@ -129,14 +142,18 @@ ProcessorState = TypedDict('ProcessorState',
 	'frame_enhancer_blend' : int,
 	'lip_syncer_model' : LipSyncerModel
 })
-ProcessorStateSet = Dict[AppContext, ProcessorState]
+ProcessorStateSet : TypeAlias = Dict[AppContext, ProcessorState]
 
-LivePortraitPitch = float
-LivePortraitYaw = float
-LivePortraitRoll = float
-LivePortraitExpression = NDArray[Any]
-LivePortraitFeatureVolume = NDArray[Any]
-LivePortraitMotionPoints = NDArray[Any]
-LivePortraitRotation = NDArray[Any]
-LivePortraitScale = NDArray[Any]
-LivePortraitTranslation = NDArray[Any]
+AgeModifierDirection : TypeAlias = NDArray[Any]
+DeepSwapperMorph : TypeAlias = NDArray[Any]
+FaceEnhancerWeight : TypeAlias = NDArray[Any]
+LipSyncerWeight : TypeAlias = NDArray[Any]
+LivePortraitPitch : TypeAlias = float
+LivePortraitYaw : TypeAlias = float
+LivePortraitRoll : TypeAlias = float
+LivePortraitExpression : TypeAlias = NDArray[Any]
+LivePortraitFeatureVolume : TypeAlias = NDArray[Any]
+LivePortraitMotionPoints : TypeAlias = NDArray[Any]
+LivePortraitRotation : TypeAlias = NDArray[Any]
+LivePortraitScale : TypeAlias = NDArray[Any]
+LivePortraitTranslation : TypeAlias = NDArray[Any]

facefusion/program.py

@@ -1,13 +1,14 @@
+import tempfile
 from argparse import ArgumentParser, HelpFormatter
 
 import facefusion.choices
 from facefusion import config, metadata, state_manager, wording
-from facefusion.common_helper import create_float_metavar, create_int_metavar
-from facefusion.execution import get_execution_provider_choices
-from facefusion.filesystem import list_directory
+from facefusion.common_helper import create_float_metavar, create_int_metavar, get_first, get_last
+from facefusion.execution import get_available_execution_providers
+from facefusion.ffmpeg import get_available_encoder_set
+from facefusion.filesystem import get_file_name, resolve_file_paths
 from facefusion.jobs import job_store
 from facefusion.processors.core import get_processors_modules
-from facefusion.program_helper import remove_args, suggest_face_detector_choices
 
 
 def create_help_formatter_small(prog : str) -> HelpFormatter:
@@ -18,40 +19,88 @@ def create_help_formatter_large(prog : str) -> HelpFormatter:
 	return HelpFormatter(prog, max_help_position = 300)
 
 
-def create_config_program() -> ArgumentParser:
+def create_config_path_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('-c', '--config-path', help = wording.get('help.config_path'), default = 'facefusion.ini')
-	job_store.register_job_keys([ 'config-path' ])
+	group_paths.add_argument('--config-path', help = wording.get('help.config_path'), default = 'facefusion.ini')
+	job_store.register_job_keys([ 'config_path' ])
 	apply_config_path(program)
 	return program
 
 
+def create_temp_path_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_paths = program.add_argument_group('paths')
+	group_paths.add_argument('--temp-path', help = wording.get('help.temp_path'), default = config.get_str_value('paths', 'temp_path', tempfile.gettempdir()))
+	job_store.register_job_keys([ 'temp_path' ])
+	return program
+
+
 def create_jobs_path_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('-j', '--jobs-path', help = wording.get('help.jobs_path'), default = config.get_str_value('paths.jobs_path', '.jobs'))
+	group_paths.add_argument('--jobs-path', help = wording.get('help.jobs_path'), default = config.get_str_value('paths', 'jobs_path', '.jobs'))
 	job_store.register_job_keys([ 'jobs_path' ])
 	return program
 
 
-def create_paths_program() -> ArgumentParser:
+def create_source_paths_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_paths = program.add_argument_group('paths')
-	group_paths.add_argument('-s', '--source-paths', help = wording.get('help.source_paths'), action = 'append', default = config.get_str_list('paths.source_paths'))
-	group_paths.add_argument('-t', '--target-path', help = wording.get('help.target_path'), default = config.get_str_value('paths.target_path'))
-	group_paths.add_argument('-o', '--output-path', help = wording.get('help.output_path'), default = config.get_str_value('paths.output_path'))
-	job_store.register_step_keys([ 'source_paths', 'target_path', 'output_path' ])
+	group_paths.add_argument('-s', '--source-paths', help = wording.get('help.source_paths'), default = config.get_str_list('paths', 'source_paths'), nargs = '+')
+	job_store.register_step_keys([ 'source_paths' ])
+	return program
+
+
+def create_target_path_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_paths = program.add_argument_group('paths')
+	group_paths.add_argument('-t', '--target-path', help = wording.get('help.target_path'), default = config.get_str_value('paths', 'target_path'))
+	job_store.register_step_keys([ 'target_path' ])
+	return program
+
+
+def create_output_path_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_paths = program.add_argument_group('paths')
+	group_paths.add_argument('-o', '--output-path', help = wording.get('help.output_path'), default = config.get_str_value('paths', 'output_path'))
+	job_store.register_step_keys([ 'output_path' ])
+	return program
+
+
+def create_source_pattern_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_patterns = program.add_argument_group('patterns')
+	group_patterns.add_argument('-s', '--source-pattern', help = wording.get('help.source_pattern'), default = config.get_str_value('patterns', 'source_pattern'))
+	job_store.register_job_keys([ 'source_pattern' ])
+	return program
+
+
+def create_target_pattern_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_patterns = program.add_argument_group('patterns')
+	group_patterns.add_argument('-t', '--target-pattern', help = wording.get('help.target_pattern'), default = config.get_str_value('patterns', 'target_pattern'))
+	job_store.register_job_keys([ 'target_pattern' ])
+	return program
+
+
+def create_output_pattern_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_patterns = program.add_argument_group('patterns')
+	group_patterns.add_argument('-o', '--output-pattern', help = wording.get('help.output_pattern'), default = config.get_str_value('patterns', 'output_pattern'))
+	job_store.register_job_keys([ 'output_pattern' ])
 	return program
 
 
 def create_face_detector_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_detector = program.add_argument_group('face detector')
-	group_face_detector.add_argument('--face-detector-model', help = wording.get('help.face_detector_model'), default = config.get_str_value('face_detector.face_detector_model', 'yoloface'), choices = facefusion.choices.face_detector_set.keys())
-	group_face_detector.add_argument('--face-detector-size', help = wording.get('help.face_detector_size'), default = config.get_str_value('face_detector.face_detector_size', '640x640'), choices = suggest_face_detector_choices(program))
-	group_face_detector.add_argument('--face-detector-angles', help = wording.get('help.face_detector_angles'), type = int, default = config.get_int_list('face_detector.face_detector_angles', '0'), choices = facefusion.choices.face_detector_angles, nargs = '+', metavar = 'FACE_DETECTOR_ANGLES')
-	group_face_detector.add_argument('--face-detector-score', help = wording.get('help.face_detector_score'), type = float, default = config.get_float_value('face_detector.face_detector_score', '0.5'), choices = facefusion.choices.face_detector_score_range, metavar = create_float_metavar(facefusion.choices.face_detector_score_range))
+	group_face_detector.add_argument('--face-detector-model', help = wording.get('help.face_detector_model'), default = config.get_str_value('face_detector', 'face_detector_model', 'yolo_face'), choices = facefusion.choices.face_detector_models)
+	known_args, _ = program.parse_known_args()
+	face_detector_size_choices = facefusion.choices.face_detector_set.get(known_args.face_detector_model)
+	group_face_detector.add_argument('--face-detector-size', help = wording.get('help.face_detector_size'), default = config.get_str_value('face_detector', 'face_detector_size', get_last(face_detector_size_choices)), choices = face_detector_size_choices)
+	group_face_detector.add_argument('--face-detector-angles', help = wording.get('help.face_detector_angles'), type = int, default = config.get_int_list('face_detector', 'face_detector_angles', '0'), choices = facefusion.choices.face_detector_angles, nargs = '+', metavar = 'FACE_DETECTOR_ANGLES')
+	group_face_detector.add_argument('--face-detector-score', help = wording.get('help.face_detector_score'), type = float, default = config.get_float_value('face_detector', 'face_detector_score', '0.5'), choices = facefusion.choices.face_detector_score_range, metavar = create_float_metavar(facefusion.choices.face_detector_score_range))
 	job_store.register_step_keys([ 'face_detector_model', 'face_detector_angles', 'face_detector_size', 'face_detector_score' ])
 	return program
 
@@ -59,8 +108,8 @@ def create_face_detector_program() -> ArgumentParser:
 def create_face_landmarker_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_landmarker = program.add_argument_group('face landmarker')
-	group_face_landmarker.add_argument('--face-landmarker-model', help = wording.get('help.face_landmarker_model'), default = config.get_str_value('face_landmarker.face_landmarker_model', '2dfan4'), choices = facefusion.choices.face_landmarker_models)
-	group_face_landmarker.add_argument('--face-landmarker-score', help = wording.get('help.face_landmarker_score'), type = float, default = config.get_float_value('face_landmarker.face_landmarker_score', '0.5'), choices = facefusion.choices.face_landmarker_score_range, metavar = create_float_metavar(facefusion.choices.face_landmarker_score_range))
+	group_face_landmarker.add_argument('--face-landmarker-model', help = wording.get('help.face_landmarker_model'), default = config.get_str_value('face_landmarker', 'face_landmarker_model', '2dfan4'), choices = facefusion.choices.face_landmarker_models)
+	group_face_landmarker.add_argument('--face-landmarker-score', help = wording.get('help.face_landmarker_score'), type = float, default = config.get_float_value('face_landmarker', 'face_landmarker_score', '0.5'), choices = facefusion.choices.face_landmarker_score_range, metavar = create_float_metavar(facefusion.choices.face_landmarker_score_range))
 	job_store.register_step_keys([ 'face_landmarker_model', 'face_landmarker_score' ])
 	return program
 
@@ -68,15 +117,15 @@ def create_face_landmarker_program() -> ArgumentParser:
 def create_face_selector_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_selector = program.add_argument_group('face selector')
-	group_face_selector.add_argument('--face-selector-mode', help = wording.get('help.face_selector_mode'), default = config.get_str_value('face_selector.face_selector_mode', 'reference'), choices = facefusion.choices.face_selector_modes)
-	group_face_selector.add_argument('--face-selector-order', help = wording.get('help.face_selector_order'), default = config.get_str_value('face_selector.face_selector_order', 'large-small'), choices = facefusion.choices.face_selector_orders)
-	group_face_selector.add_argument('--face-selector-age-start', help = wording.get('help.face_selector_age_start'), type = int, default = config.get_int_value('face_selector.face_selector_age_start'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
-	group_face_selector.add_argument('--face-selector-age-end', help = wording.get('help.face_selector_age_end'), type = int, default = config.get_int_value('face_selector.face_selector_age_end'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
-	group_face_selector.add_argument('--face-selector-gender', help = wording.get('help.face_selector_gender'), default = config.get_str_value('face_selector.face_selector_gender'), choices = facefusion.choices.face_selector_genders)
-	group_face_selector.add_argument('--face-selector-race', help = wording.get('help.face_selector_race'), default = config.get_str_value('face_selector.face_selector_race'), choices = facefusion.choices.face_selector_races)
-	group_face_selector.add_argument('--reference-face-position', help = wording.get('help.reference_face_position'), type = int, default = config.get_int_value('face_selector.reference_face_position', '0'))
-	group_face_selector.add_argument('--reference-face-distance', help = wording.get('help.reference_face_distance'), type = float, default = config.get_float_value('face_selector.reference_face_distance', '0.6'), choices = facefusion.choices.reference_face_distance_range, metavar = create_float_metavar(facefusion.choices.reference_face_distance_range))
-	group_face_selector.add_argument('--reference-frame-number', help = wording.get('help.reference_frame_number'), type = int, default = config.get_int_value('face_selector.reference_frame_number', '0'))
+	group_face_selector.add_argument('--face-selector-mode', help = wording.get('help.face_selector_mode'), default = config.get_str_value('face_selector', 'face_selector_mode', 'reference'), choices = facefusion.choices.face_selector_modes)
+	group_face_selector.add_argument('--face-selector-order', help = wording.get('help.face_selector_order'), default = config.get_str_value('face_selector', 'face_selector_order', 'large-small'), choices = facefusion.choices.face_selector_orders)
+	group_face_selector.add_argument('--face-selector-age-start', help = wording.get('help.face_selector_age_start'), type = int, default = config.get_int_value('face_selector', 'face_selector_age_start'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
+	group_face_selector.add_argument('--face-selector-age-end', help = wording.get('help.face_selector_age_end'), type = int, default = config.get_int_value('face_selector', 'face_selector_age_end'), choices = facefusion.choices.face_selector_age_range, metavar = create_int_metavar(facefusion.choices.face_selector_age_range))
+	group_face_selector.add_argument('--face-selector-gender', help = wording.get('help.face_selector_gender'), default = config.get_str_value('face_selector', 'face_selector_gender'), choices = facefusion.choices.face_selector_genders)
+	group_face_selector.add_argument('--face-selector-race', help = wording.get('help.face_selector_race'), default = config.get_str_value('face_selector', 'face_selector_race'), choices = facefusion.choices.face_selector_races)
+	group_face_selector.add_argument('--reference-face-position', help = wording.get('help.reference_face_position'), type = int, default = config.get_int_value('face_selector', 'reference_face_position', '0'))
+	group_face_selector.add_argument('--reference-face-distance', help = wording.get('help.reference_face_distance'), type = float, default = config.get_float_value('face_selector', 'reference_face_distance', '0.3'), choices = facefusion.choices.reference_face_distance_range, metavar = create_float_metavar(facefusion.choices.reference_face_distance_range))
+	group_face_selector.add_argument('--reference-frame-number', help = wording.get('help.reference_frame_number'), type = int, default = config.get_int_value('face_selector', 'reference_frame_number', '0'))
 	job_store.register_step_keys([ 'face_selector_mode', 'face_selector_order', 'face_selector_gender', 'face_selector_race', 'face_selector_age_start', 'face_selector_age_end', 'reference_face_position', 'reference_face_distance', 'reference_frame_number' ])
 	return program
 
@@ -84,46 +133,51 @@ def create_face_selector_program() -> ArgumentParser:
 def create_face_masker_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_face_masker = program.add_argument_group('face masker')
-	group_face_masker.add_argument('--face-mask-types', help = wording.get('help.face_mask_types').format(choices = ', '.join(facefusion.choices.face_mask_types)), default = config.get_str_list('face_masker.face_mask_types', 'box'), choices = facefusion.choices.face_mask_types, nargs = '+', metavar = 'FACE_MASK_TYPES')
-	group_face_masker.add_argument('--face-mask-blur', help = wording.get('help.face_mask_blur'), type = float, default = config.get_float_value('face_masker.face_mask_blur', '0.3'), choices = facefusion.choices.face_mask_blur_range, metavar = create_float_metavar(facefusion.choices.face_mask_blur_range))
-	group_face_masker.add_argument('--face-mask-padding', help = wording.get('help.face_mask_padding'), type = int, default = config.get_int_list('face_masker.face_mask_padding', '0 0 0 0'), nargs = '+')
-	group_face_masker.add_argument('--face-mask-regions', help = wording.get('help.face_mask_regions').format(choices = ', '.join(facefusion.choices.face_mask_regions)), default = config.get_str_list('face_masker.face_mask_regions', ' '.join(facefusion.choices.face_mask_regions)), choices = facefusion.choices.face_mask_regions, nargs = '+', metavar = 'FACE_MASK_REGIONS')
-	job_store.register_step_keys([ 'face_mask_types', 'face_mask_blur', 'face_mask_padding', 'face_mask_regions' ])
+	group_face_masker.add_argument('--face-occluder-model', help = wording.get('help.face_occluder_model'), default = config.get_str_value('face_masker', 'face_occluder_model', 'xseg_1'), choices = facefusion.choices.face_occluder_models)
+	group_face_masker.add_argument('--face-parser-model', help = wording.get('help.face_parser_model'), default = config.get_str_value('face_masker', 'face_parser_model', 'bisenet_resnet_34'), choices = facefusion.choices.face_parser_models)
+	group_face_masker.add_argument('--face-mask-types', help = wording.get('help.face_mask_types').format(choices = ', '.join(facefusion.choices.face_mask_types)), default = config.get_str_list('face_masker', 'face_mask_types', 'box'), choices = facefusion.choices.face_mask_types, nargs = '+', metavar = 'FACE_MASK_TYPES')
+	group_face_masker.add_argument('--face-mask-areas', help = wording.get('help.face_mask_areas').format(choices = ', '.join(facefusion.choices.face_mask_areas)), default = config.get_str_list('face_masker', 'face_mask_areas', ' '.join(facefusion.choices.face_mask_areas)), choices = facefusion.choices.face_mask_areas, nargs = '+', metavar = 'FACE_MASK_AREAS')
+	group_face_masker.add_argument('--face-mask-regions', help = wording.get('help.face_mask_regions').format(choices = ', '.join(facefusion.choices.face_mask_regions)), default = config.get_str_list('face_masker', 'face_mask_regions', ' '.join(facefusion.choices.face_mask_regions)), choices = facefusion.choices.face_mask_regions, nargs = '+', metavar = 'FACE_MASK_REGIONS')
+	group_face_masker.add_argument('--face-mask-blur', help = wording.get('help.face_mask_blur'), type = float, default = config.get_float_value('face_masker', 'face_mask_blur', '0.3'), choices = facefusion.choices.face_mask_blur_range, metavar = create_float_metavar(facefusion.choices.face_mask_blur_range))
+	group_face_masker.add_argument('--face-mask-padding', help = wording.get('help.face_mask_padding'), type = int, default = config.get_int_list('face_masker', 'face_mask_padding', '0 0 0 0'), nargs = '+')
+	job_store.register_step_keys([ 'face_occluder_model', 'face_parser_model', 'face_mask_types', 'face_mask_areas', 'face_mask_regions', 'face_mask_blur', 'face_mask_padding' ])
 	return program
 
 
 def create_frame_extraction_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_frame_extraction = program.add_argument_group('frame extraction')
-	group_frame_extraction.add_argument('--trim-frame-start', help = wording.get('help.trim_frame_start'), type = int, default = facefusion.config.get_int_value('frame_extraction.trim_frame_start'))
-	group_frame_extraction.add_argument('--trim-frame-end',	help = wording.get('help.trim_frame_end'), type = int, default = facefusion.config.get_int_value('frame_extraction.trim_frame_end'))
-	group_frame_extraction.add_argument('--temp-frame-format', help = wording.get('help.temp_frame_format'), default = config.get_str_value('frame_extraction.temp_frame_format', 'png'), choices = facefusion.choices.temp_frame_formats)
-	group_frame_extraction.add_argument('--keep-temp', help = wording.get('help.keep_temp'), action = 'store_true',	default = config.get_bool_value('frame_extraction.keep_temp'))
+	group_frame_extraction.add_argument('--trim-frame-start', help = wording.get('help.trim_frame_start'), type = int, default = facefusion.config.get_int_value('frame_extraction', 'trim_frame_start'))
+	group_frame_extraction.add_argument('--trim-frame-end', help = wording.get('help.trim_frame_end'), type = int, default = facefusion.config.get_int_value('frame_extraction', 'trim_frame_end'))
+	group_frame_extraction.add_argument('--temp-frame-format', help = wording.get('help.temp_frame_format'), default = config.get_str_value('frame_extraction', 'temp_frame_format', 'png'), choices = facefusion.choices.temp_frame_formats)
+	group_frame_extraction.add_argument('--keep-temp', help = wording.get('help.keep_temp'), action = 'store_true', default = config.get_bool_value('frame_extraction', 'keep_temp'))
 	job_store.register_step_keys([ 'trim_frame_start', 'trim_frame_end', 'temp_frame_format', 'keep_temp' ])
 	return program
 
 
 def create_output_creation_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
+	available_encoder_set = get_available_encoder_set()
 	group_output_creation = program.add_argument_group('output creation')
-	group_output_creation.add_argument('--output-image-quality', help = wording.get('help.output_image_quality'), type = int, default = config.get_int_value('output_creation.output_image_quality', '80'), choices = facefusion.choices.output_image_quality_range, metavar = create_int_metavar(facefusion.choices.output_image_quality_range))
-	group_output_creation.add_argument('--output-image-resolution', help = wording.get('help.output_image_resolution'), default = config.get_str_value('output_creation.output_image_resolution'))
-	group_output_creation.add_argument('--output-audio-encoder', help = wording.get('help.output_audio_encoder'), default = config.get_str_value('output_creation.output_audio_encoder', 'aac'), choices = facefusion.choices.output_audio_encoders)
-	group_output_creation.add_argument('--output-video-encoder', help = wording.get('help.output_video_encoder'), default = config.get_str_value('output_creation.output_video_encoder', 'libx264'), choices = facefusion.choices.output_video_encoders)
-	group_output_creation.add_argument('--output-video-preset', help = wording.get('help.output_video_preset'), default = config.get_str_value('output_creation.output_video_preset', 'veryfast'), choices = facefusion.choices.output_video_presets)
-	group_output_creation.add_argument('--output-video-quality', help = wording.get('help.output_video_quality'), type = int, default = config.get_int_value('output_creation.output_video_quality', '80'), choices = facefusion.choices.output_video_quality_range, metavar = create_int_metavar(facefusion.choices.output_video_quality_range))
-	group_output_creation.add_argument('--output-video-resolution', help = wording.get('help.output_video_resolution'), default = config.get_str_value('output_creation.output_video_resolution'))
-	group_output_creation.add_argument('--output-video-fps', help = wording.get('help.output_video_fps'), type = float, default = config.get_str_value('output_creation.output_video_fps'))
-	group_output_creation.add_argument('--skip-audio', help = wording.get('help.skip_audio'), action = 'store_true', default = config.get_bool_value('output_creation.skip_audio'))
-	job_store.register_step_keys([ 'output_image_quality', 'output_image_resolution', 'output_audio_encoder', 'output_video_encoder', 'output_video_preset', 'output_video_quality', 'output_video_resolution', 'output_video_fps', 'skip_audio' ])
+	group_output_creation.add_argument('--output-image-quality', help = wording.get('help.output_image_quality'), type = int, default = config.get_int_value('output_creation', 'output_image_quality', '80'), choices = facefusion.choices.output_image_quality_range, metavar = create_int_metavar(facefusion.choices.output_image_quality_range))
+	group_output_creation.add_argument('--output-image-resolution', help = wording.get('help.output_image_resolution'), default = config.get_str_value('output_creation', 'output_image_resolution'))
+	group_output_creation.add_argument('--output-audio-encoder', help = wording.get('help.output_audio_encoder'), default = config.get_str_value('output_creation', 'output_audio_encoder', get_first(available_encoder_set.get('audio'))), choices = available_encoder_set.get('audio'))
+	group_output_creation.add_argument('--output-audio-quality', help = wording.get('help.output_audio_quality'), type = int, default = config.get_int_value('output_creation', 'output_audio_quality', '80'), choices = facefusion.choices.output_audio_quality_range, metavar = create_int_metavar(facefusion.choices.output_audio_quality_range))
+	group_output_creation.add_argument('--output-audio-volume', help = wording.get('help.output_audio_volume'), type = int, default = config.get_int_value('output_creation', 'output_audio_volume', '100'), choices = facefusion.choices.output_audio_volume_range, metavar = create_int_metavar(facefusion.choices.output_audio_volume_range))
+	group_output_creation.add_argument('--output-video-encoder', help = wording.get('help.output_video_encoder'), default = config.get_str_value('output_creation', 'output_video_encoder', get_first(available_encoder_set.get('video'))), choices = available_encoder_set.get('video'))
+	group_output_creation.add_argument('--output-video-preset', help = wording.get('help.output_video_preset'), default = config.get_str_value('output_creation', 'output_video_preset', 'veryfast'), choices = facefusion.choices.output_video_presets)
+	group_output_creation.add_argument('--output-video-quality', help = wording.get('help.output_video_quality'), type = int, default = config.get_int_value('output_creation', 'output_video_quality', '80'), choices = facefusion.choices.output_video_quality_range, metavar = create_int_metavar(facefusion.choices.output_video_quality_range))
+	group_output_creation.add_argument('--output-video-resolution', help = wording.get('help.output_video_resolution'), default = config.get_str_value('output_creation', 'output_video_resolution'))
+	group_output_creation.add_argument('--output-video-fps', help = wording.get('help.output_video_fps'), type = float, default = config.get_str_value('output_creation', 'output_video_fps'))
+	job_store.register_step_keys([ 'output_image_quality', 'output_image_resolution', 'output_audio_encoder', 'output_audio_quality', 'output_audio_volume', 'output_video_encoder', 'output_video_preset', 'output_video_quality', 'output_video_resolution', 'output_video_fps' ])
 	return program
 
 
 def create_processors_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	available_processors = list_directory('facefusion/processors/modules')
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
 	group_processors = program.add_argument_group('processors')
-	group_processors.add_argument('--processors', help = wording.get('help.processors').format(choices = ', '.join(available_processors)), default = config.get_str_list('processors.processors', 'face_swapper'), nargs = '+')
+	group_processors.add_argument('--processors', help = wording.get('help.processors').format(choices = ', '.join(available_processors)), default = config.get_str_list('processors', 'processors', 'face_swapper'), nargs = '+')
 	job_store.register_step_keys([ 'processors' ])
 	for processor_module in get_processors_modules(available_processors):
 		processor_module.register_args(program)
@@ -132,22 +186,46 @@ def create_processors_program() -> ArgumentParser:
 
 def create_uis_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	available_ui_layouts = list_directory('facefusion/uis/layouts')
+	available_ui_layouts = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/uis/layouts') ]
 	group_uis = program.add_argument_group('uis')
-	group_uis.add_argument('--open-browser', help = wording.get('help.open_browser'), action = 'store_true', default = config.get_bool_value('uis.open_browser'))
-	group_uis.add_argument('--ui-layouts', help = wording.get('help.ui_layouts').format(choices = ', '.join(available_ui_layouts)), default = config.get_str_list('uis.ui_layouts', 'default'), nargs = '+')
-	group_uis.add_argument('--ui-workflow', help = wording.get('help.ui_workflow'), default = config.get_str_value('uis.ui_workflow', 'instant_runner'), choices = facefusion.choices.ui_workflows)
+	group_uis.add_argument('--open-browser', help = wording.get('help.open_browser'), action = 'store_true', default = config.get_bool_value('uis', 'open_browser'))
+	group_uis.add_argument('--ui-layouts', help = wording.get('help.ui_layouts').format(choices = ', '.join(available_ui_layouts)), default = config.get_str_list('uis', 'ui_layouts', 'default'), nargs = '+')
+	group_uis.add_argument('--ui-workflow', help = wording.get('help.ui_workflow'), default = config.get_str_value('uis', 'ui_workflow', 'instant_runner'), choices = facefusion.choices.ui_workflows)
+	return program
+
+
+def create_download_providers_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_download = program.add_argument_group('download')
+	group_download.add_argument('--download-providers', help = wording.get('help.download_providers').format(choices = ', '.join(facefusion.choices.download_providers)), default = config.get_str_list('download', 'download_providers', ' '.join(facefusion.choices.download_providers)), choices = facefusion.choices.download_providers, nargs = '+', metavar = 'DOWNLOAD_PROVIDERS')
+	job_store.register_job_keys([ 'download_providers' ])
+	return program
+
+
+def create_download_scope_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_download = program.add_argument_group('download')
+	group_download.add_argument('--download-scope', help = wording.get('help.download_scope'), default = config.get_str_value('download', 'download_scope', 'lite'), choices = facefusion.choices.download_scopes)
+	job_store.register_job_keys([ 'download_scope' ])
+	return program
+
+
+def create_benchmark_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_benchmark = program.add_argument_group('benchmark')
+	group_benchmark.add_argument('--benchmark-resolutions', help = wording.get('help.benchmark_resolutions'), default = config.get_str_list('benchmark', 'benchmark_resolutions', get_first(facefusion.choices.benchmark_resolutions)), choices = facefusion.choices.benchmark_resolutions, nargs = '+')
+	group_benchmark.add_argument('--benchmark-cycle-count', help = wording.get('help.benchmark_cycle_count'), type = int, default = config.get_int_value('benchmark', 'benchmark_cycle_count', '5'), choices = facefusion.choices.benchmark_cycle_count_range)
 	return program
 
 
 def create_execution_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
-	execution_providers = get_execution_provider_choices()
+	available_execution_providers = get_available_execution_providers()
 	group_execution = program.add_argument_group('execution')
-	group_execution.add_argument('--execution-device-id', help = wording.get('help.execution_device_id'), default = config.get_str_value('execution.execution_device_id', '0'))
-	group_execution.add_argument('--execution-providers', help = wording.get('help.execution_providers').format(choices = ', '.join(execution_providers)), default = config.get_str_list('execution.execution_providers', 'cpu'), choices = execution_providers, nargs = '+', metavar = 'EXECUTION_PROVIDERS')
-	group_execution.add_argument('--execution-thread-count', help = wording.get('help.execution_thread_count'), type = int, default = config.get_int_value('execution.execution_thread_count', '4'), choices = facefusion.choices.execution_thread_count_range, metavar = create_int_metavar(facefusion.choices.execution_thread_count_range))
-	group_execution.add_argument('--execution-queue-count', help = wording.get('help.execution_queue_count'), type = int, default = config.get_int_value('execution.execution_queue_count', '1'), choices = facefusion.choices.execution_queue_count_range, metavar = create_int_metavar(facefusion.choices.execution_queue_count_range))
+	group_execution.add_argument('--execution-device-id', help = wording.get('help.execution_device_id'), default = config.get_str_value('execution', 'execution_device_id', '0'))
+	group_execution.add_argument('--execution-providers', help = wording.get('help.execution_providers').format(choices = ', '.join(available_execution_providers)), default = config.get_str_list('execution', 'execution_providers', get_first(available_execution_providers)), choices = available_execution_providers, nargs = '+', metavar = 'EXECUTION_PROVIDERS')
+	group_execution.add_argument('--execution-thread-count', help = wording.get('help.execution_thread_count'), type = int, default = config.get_int_value('execution', 'execution_thread_count', '4'), choices = facefusion.choices.execution_thread_count_range, metavar = create_int_metavar(facefusion.choices.execution_thread_count_range))
+	group_execution.add_argument('--execution-queue-count', help = wording.get('help.execution_queue_count'), type = int, default = config.get_int_value('execution', 'execution_queue_count', '1'), choices = facefusion.choices.execution_queue_count_range, metavar = create_int_metavar(facefusion.choices.execution_queue_count_range))
 	job_store.register_job_keys([ 'execution_device_id', 'execution_providers', 'execution_thread_count', 'execution_queue_count' ])
 	return program
 
@@ -155,28 +233,28 @@ def create_execution_program() -> ArgumentParser:
 def create_memory_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_memory = program.add_argument_group('memory')
-	group_memory.add_argument('--video-memory-strategy', help = wording.get('help.video_memory_strategy'), default = config.get_str_value('memory.video_memory_strategy', 'strict'), choices = facefusion.choices.video_memory_strategies)
-	group_memory.add_argument('--system-memory-limit', help = wording.get('help.system_memory_limit'), type = int, default = config.get_int_value('memory.system_memory_limit', '0'), choices = facefusion.choices.system_memory_limit_range, metavar = create_int_metavar(facefusion.choices.system_memory_limit_range))
+	group_memory.add_argument('--video-memory-strategy', help = wording.get('help.video_memory_strategy'), default = config.get_str_value('memory', 'video_memory_strategy', 'strict'), choices = facefusion.choices.video_memory_strategies)
+	group_memory.add_argument('--system-memory-limit', help = wording.get('help.system_memory_limit'), type = int, default = config.get_int_value('memory', 'system_memory_limit', '0'), choices = facefusion.choices.system_memory_limit_range, metavar = create_int_metavar(facefusion.choices.system_memory_limit_range))
 	job_store.register_job_keys([ 'video_memory_strategy', 'system_memory_limit' ])
 	return program
 
 
-def create_skip_download_program() -> ArgumentParser:
-	program = ArgumentParser(add_help = False)
-	group_misc = program.add_argument_group('misc')
-	group_misc.add_argument('--skip-download', help = wording.get('help.skip_download'), action = 'store_true', default = config.get_bool_value('misc.skip_download'))
-	job_store.register_job_keys([ 'skip_download' ])
-	return program
-
-
 def create_log_level_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	group_misc = program.add_argument_group('misc')
-	group_misc.add_argument('--log-level', help = wording.get('help.log_level'), default = config.get_str_value('misc.log_level', 'info'), choices = facefusion.choices.log_level_set.keys())
+	group_misc.add_argument('--log-level', help = wording.get('help.log_level'), default = config.get_str_value('misc', 'log_level', 'info'), choices = facefusion.choices.log_levels)
 	job_store.register_job_keys([ 'log_level' ])
 	return program
 
 
+def create_halt_on_error_program() -> ArgumentParser:
+	program = ArgumentParser(add_help = False)
+	group_misc = program.add_argument_group('misc')
+	group_misc.add_argument('--halt-on-error', help = wording.get('help.halt_on_error'), action = 'store_true', default = config.get_bool_value('misc', 'halt_on_error'))
+	job_store.register_job_keys([ 'halt_on_error' ])
+	return program
+
+
 def create_job_id_program() -> ArgumentParser:
 	program = ArgumentParser(add_help = False)
 	program.add_argument('job_id', help = wording.get('help.job_id'))
@@ -197,11 +275,11 @@ def create_step_index_program() -> ArgumentParser:
 
 
 def collect_step_program() -> ArgumentParser:
-	return ArgumentParser(parents= [ create_config_program(), create_jobs_path_program(), create_paths_program(), create_face_detector_program(), create_face_landmarker_program(), create_face_selector_program(), create_face_masker_program(), create_frame_extraction_program(), create_output_creation_program(), create_processors_program() ], add_help = False)
+	return ArgumentParser(parents = [ create_face_detector_program(), create_face_landmarker_program(), create_face_selector_program(), create_face_masker_program(), create_frame_extraction_program(), create_output_creation_program(), create_processors_program() ], add_help = False)
 
 
 def collect_job_program() -> ArgumentParser:
-	return ArgumentParser(parents= [ create_execution_program(), create_memory_program(), create_skip_download_program(), create_log_level_program() ], add_help = False)
+	return ArgumentParser(parents = [ create_execution_program(), create_download_providers_program(), create_memory_program(), create_log_level_program() ], add_help = False)
 
 
 def create_program() -> ArgumentParser:
@@ -210,26 +288,28 @@ def create_program() -> ArgumentParser:
 	program.add_argument('-v', '--version', version = metadata.get('name') + ' ' + metadata.get('version'), action = 'version')
 	sub_program = program.add_subparsers(dest = 'command')
 	# general
-	sub_program.add_parser('run', help = wording.get('help.run'), parents = [ collect_step_program(), create_uis_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('headless-run', help = wording.get('help.headless_run'), parents = [ collect_step_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('force-download', help = wording.get('help.force_download'), parents = [ create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('run', help = wording.get('help.run'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_uis_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('headless-run', help = wording.get('help.headless_run'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('batch-run', help = wording.get('help.batch_run'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), create_source_pattern_program(), create_target_pattern_program(), create_output_pattern_program(), collect_step_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('force-download', help = wording.get('help.force_download'), parents = [ create_download_providers_program(), create_download_scope_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('benchmark', help = wording.get('help.benchmark'), parents = [ create_temp_path_program(), collect_step_program(), create_benchmark_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
 	# job manager
 	sub_program.add_parser('job-list', help = wording.get('help.job_list'), parents = [ create_job_status_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
 	sub_program.add_parser('job-create', help = wording.get('help.job_create'), parents = [ create_job_id_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
 	sub_program.add_parser('job-submit', help = wording.get('help.job_submit'), parents = [ create_job_id_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-submit-all', help = wording.get('help.job_submit_all'), parents = [ create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-submit-all', help = wording.get('help.job_submit_all'), parents = [ create_jobs_path_program(), create_log_level_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
 	sub_program.add_parser('job-delete', help = wording.get('help.job_delete'), parents = [ create_job_id_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-delete-all', help = wording.get('help.job_delete_all'), parents = [ create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-add-step', help = wording.get('help.job_add_step'), parents = [ create_job_id_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-remix-step', help = wording.get('help.job_remix_step'), parents = [ create_job_id_program(), create_step_index_program(), remove_args(collect_step_program(), [ 'target_path' ]), create_log_level_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-insert-step', help = wording.get('help.job_insert_step'), parents = [ create_job_id_program(), create_step_index_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-delete-all', help = wording.get('help.job_delete_all'), parents = [ create_jobs_path_program(), create_log_level_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-add-step', help = wording.get('help.job_add_step'), parents = [ create_job_id_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-remix-step', help = wording.get('help.job_remix_step'), parents = [ create_job_id_program(), create_step_index_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_output_path_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-insert-step', help = wording.get('help.job_insert_step'), parents = [ create_job_id_program(), create_step_index_program(), create_config_path_program(), create_jobs_path_program(), create_source_paths_program(), create_target_path_program(), create_output_path_program(), collect_step_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
 	sub_program.add_parser('job-remove-step', help = wording.get('help.job_remove_step'), parents = [ create_job_id_program(), create_step_index_program(), create_jobs_path_program(), create_log_level_program() ], formatter_class = create_help_formatter_large)
 	# job runner
-	sub_program.add_parser('job-run', help = wording.get('help.job_run'), parents = [ create_job_id_program(), create_config_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-run-all', help = wording.get('help.job_run_all'), parents = [ create_config_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-retry', help = wording.get('help.job_retry'), parents = [ create_job_id_program(), create_config_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	sub_program.add_parser('job-retry-all', help = wording.get('help.job_retry_all'), parents = [ create_config_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
-	return ArgumentParser(parents = [ program ], formatter_class = create_help_formatter_small, add_help = True)
+	sub_program.add_parser('job-run', help = wording.get('help.job_run'), parents = [ create_job_id_program(), create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-run-all', help = wording.get('help.job_run_all'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-retry', help = wording.get('help.job_retry'), parents = [ create_job_id_program(), create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program() ], formatter_class = create_help_formatter_large)
+	sub_program.add_parser('job-retry-all', help = wording.get('help.job_retry_all'), parents = [ create_config_path_program(), create_temp_path_program(), create_jobs_path_program(), collect_job_program(), create_halt_on_error_program() ], formatter_class = create_help_formatter_large)
+	return ArgumentParser(parents = [ program ], formatter_class = create_help_formatter_small)
 
 
 def apply_config_path(program : ArgumentParser) -> None:

facefusion/program_helper.py

@@ -1,8 +1,5 @@
 from argparse import ArgumentParser, _ArgumentGroup, _SubParsersAction
-from typing import List, Optional
-
-import facefusion.choices
-from facefusion.processors import choices as processors_choices
+from typing import Optional
 
 
 def find_argument_group(program : ArgumentParser, group_name : str) -> Optional[_ArgumentGroup]:
@@ -32,21 +29,3 @@ def validate_actions(program : ArgumentParser) -> bool:
 			elif action.default not in action.choices:
 				return False
 	return True
-
-
-def remove_args(program : ArgumentParser, remove_names : List[str]) -> ArgumentParser:
-	actions = [ action for action in program._actions if action.dest in remove_names ]
-
-	for action in actions:
-		program._actions.remove(action)
-	return program
-
-
-def suggest_face_detector_choices(program : ArgumentParser) -> List[str]:
-	known_args, _ = program.parse_known_args()
-	return facefusion.choices.face_detector_set.get(known_args.face_detector_model) #type:ignore[call-overload]
-
-
-def suggest_face_swapper_pixel_boost_choices(program : ArgumentParser) -> List[str]:
-	known_args, _ = program.parse_known_args()
-	return processors_choices.face_swapper_set.get(known_args.face_swapper_model) #type:ignore[call-overload]

facefusion/state_manager.py

@@ -1,37 +1,37 @@
 from typing import Any, Union
 
 from facefusion.app_context import detect_app_context
-from facefusion.processors.typing import ProcessorState, ProcessorStateKey
-from facefusion.typing import State, StateKey, StateSet
+from facefusion.processors.types import ProcessorState, ProcessorStateKey, ProcessorStateSet
+from facefusion.types import State, StateKey, StateSet
 
-STATES : Union[StateSet, ProcessorState] =\
+STATE_SET : Union[StateSet, ProcessorStateSet] =\
 {
-	'cli': {}, #type:ignore[typeddict-item]
-	'ui': {} #type:ignore[typeddict-item]
+	'cli': {}, #type:ignore[assignment]
+	'ui': {} #type:ignore[assignment]
 }
 
 
 def get_state() -> Union[State, ProcessorState]:
 	app_context = detect_app_context()
-	return STATES.get(app_context) #type:ignore
+	return STATE_SET.get(app_context)
 
 
 def init_item(key : Union[StateKey, ProcessorStateKey], value : Any) -> None:
-	STATES['cli'][key] = value #type:ignore
-	STATES['ui'][key] = value #type:ignore
+	STATE_SET['cli'][key] = value #type:ignore[literal-required]
+	STATE_SET['ui'][key] = value #type:ignore[literal-required]
 
 
 def get_item(key : Union[StateKey, ProcessorStateKey]) -> Any:
-	return get_state().get(key) #type:ignore
+	return get_state().get(key) #type:ignore[literal-required]
 
 
 def set_item(key : Union[StateKey, ProcessorStateKey], value : Any) -> None:
 	app_context = detect_app_context()
-	STATES[app_context][key] = value #type:ignore
+	STATE_SET[app_context][key] = value #type:ignore[literal-required]
 
 
 def sync_item(key : Union[StateKey, ProcessorStateKey]) -> None:
-	STATES['cli'][key] = STATES.get('ui').get(key) #type:ignore
+	STATE_SET['cli'][key] = STATE_SET.get('ui').get(key) #type:ignore[literal-required]
 
 
 def clear_item(key : Union[StateKey, ProcessorStateKey]) -> None:

facefusion/statistics.py

@@ -1,51 +0,0 @@
-from typing import Any, Dict
-
-import numpy
-
-from facefusion import logger, state_manager
-from facefusion.face_store import get_face_store
-from facefusion.typing import FaceSet
-
-
-def create_statistics(static_faces : FaceSet) -> Dict[str, Any]:
-	face_detector_scores = []
-	face_landmarker_scores = []
-	statistics =\
-	{
-		'min_face_detector_score': 0,
-		'min_face_landmarker_score': 0,
-		'max_face_detector_score': 0,
-		'max_face_landmarker_score': 0,
-		'average_face_detector_score': 0,
-		'average_face_landmarker_score': 0,
-		'total_face_landmark_5_fallbacks': 0,
-		'total_frames_with_faces': 0,
-		'total_faces': 0
-	}
-
-	for faces in static_faces.values():
-		statistics['total_frames_with_faces'] = statistics.get('total_frames_with_faces') + 1
-		for face in faces:
-			statistics['total_faces'] = statistics.get('total_faces') + 1
-			face_detector_scores.append(face.score_set.get('detector'))
-			face_landmarker_scores.append(face.score_set.get('landmarker'))
-			if numpy.array_equal(face.landmark_set.get('5'), face.landmark_set.get('5/68')):
-				statistics['total_face_landmark_5_fallbacks'] = statistics.get('total_face_landmark_5_fallbacks') + 1
-
-	if face_detector_scores:
-		statistics['min_face_detector_score'] = round(min(face_detector_scores), 2)
-		statistics['max_face_detector_score'] = round(max(face_detector_scores), 2)
-		statistics['average_face_detector_score'] = round(numpy.mean(face_detector_scores), 2)
-	if face_landmarker_scores:
-		statistics['min_face_landmarker_score'] = round(min(face_landmarker_scores), 2)
-		statistics['max_face_landmarker_score'] = round(max(face_landmarker_scores), 2)
-		statistics['average_face_landmarker_score'] = round(numpy.mean(face_landmarker_scores), 2)
-	return statistics
-
-
-def conditional_log_statistics() -> None:
-	if state_manager.get_item('log_level') == 'debug':
-		statistics = create_statistics(get_face_store().get('static_faces'))
-
-		for name, value in statistics.items():
-			logger.debug(str(name) + ': ' + str(value), __name__)

facefusion/temp_helper.py

@@ -1,15 +1,13 @@
-import glob
 import os
-import tempfile
 from typing import List
 
 from facefusion import state_manager
-from facefusion.filesystem import create_directory, move_file, remove_directory
+from facefusion.filesystem import create_directory, get_file_extension, get_file_name, move_file, remove_directory, resolve_file_pattern
 
 
 def get_temp_file_path(file_path : str) -> str:
-	_, temp_file_extension = os.path.splitext(os.path.basename(file_path))
 	temp_directory_path = get_temp_directory_path(file_path)
+	temp_file_extension = get_file_extension(file_path)
 	return os.path.join(temp_directory_path, 'temp' + temp_file_extension)
 
 
@@ -18,9 +16,9 @@ def move_temp_file(file_path : str, move_path : str) -> bool:
 	return move_file(temp_file_path, move_path)
 
 
-def get_temp_frame_paths(target_path : str) -> List[str]:
+def resolve_temp_frame_paths(target_path : str) -> List[str]:
 	temp_frames_pattern = get_temp_frames_pattern(target_path, '*')
-	return sorted(glob.glob(temp_frames_pattern))
+	return resolve_file_pattern(temp_frames_pattern)
 
 
 def get_temp_frames_pattern(target_path : str, temp_frame_prefix : str) -> str:
@@ -28,24 +26,9 @@ def get_temp_frames_pattern(target_path : str, temp_frame_prefix : str) -> str:
 	return os.path.join(temp_directory_path, temp_frame_prefix + '.' + state_manager.get_item('temp_frame_format'))
 
 
-def get_base_directory_path() -> str:
-	return os.path.join(tempfile.gettempdir(), 'facefusion')
-
-
-def create_base_directory() -> bool:
-	base_directory_path = get_base_directory_path()
-	return create_directory(base_directory_path)
-
-
-def clear_base_directory() -> bool:
-	base_directory_path = get_base_directory_path()
-	return remove_directory(base_directory_path)
-
-
 def get_temp_directory_path(file_path : str) -> str:
-	temp_file_name, _ = os.path.splitext(os.path.basename(file_path))
-	base_directory_path = get_base_directory_path()
-	return os.path.join(base_directory_path, temp_file_name)
+	temp_file_name = get_file_name(file_path)
+	return os.path.join(state_manager.get_item('temp_path'), 'facefusion', temp_file_name)
 
 
 def create_temp_directory(file_path : str) -> bool:

facefusion/types.py

@@ -1,20 +1,21 @@
 from collections import namedtuple
-from typing import Any, Callable, Dict, List, Literal, Optional, Tuple, TypedDict
+from typing import Any, Callable, Dict, List, Literal, Optional, Tuple, TypeAlias, TypedDict
 
+import cv2
 import numpy
 from numpy.typing import NDArray
 from onnxruntime import InferenceSession
 
-Scale = float
-Score = float
-Angle = int
+Scale : TypeAlias = float
+Score : TypeAlias = float
+Angle : TypeAlias = int
 
-Detection = NDArray[Any]
-Prediction = NDArray[Any]
+Detection : TypeAlias = NDArray[Any]
+Prediction : TypeAlias = NDArray[Any]
 
-BoundingBox = NDArray[Any]
-FaceLandmark5 = NDArray[Any]
-FaceLandmark68 = NDArray[Any]
+BoundingBox : TypeAlias = NDArray[Any]
+FaceLandmark5 : TypeAlias = NDArray[Any]
+FaceLandmark68 : TypeAlias = NDArray[Any]
 FaceLandmarkSet = TypedDict('FaceLandmarkSet',
 {
 	'5' : FaceLandmark5, #type:ignore[valid-type]
@@ -27,9 +28,9 @@ FaceScoreSet = TypedDict('FaceScoreSet',
 	'detector' : Score,
 	'landmarker' : Score
 })
-Embedding = NDArray[numpy.float64]
+Embedding : TypeAlias = NDArray[numpy.float64]
 Gender = Literal['female', 'male']
-Age = range
+Age : TypeAlias = range
 Race = Literal['white', 'black', 'latino', 'asian', 'indian', 'arabic']
 Face = namedtuple('Face',
 [
@@ -43,33 +44,35 @@ Face = namedtuple('Face',
 	'age',
 	'race'
 ])
-FaceSet = Dict[str, List[Face]]
+FaceSet : TypeAlias = Dict[str, List[Face]]
 FaceStore = TypedDict('FaceStore',
 {
 	'static_faces' : FaceSet,
 	'reference_faces' : FaceSet
 })
+VideoPoolSet : TypeAlias = Dict[str, cv2.VideoCapture]
 
-VisionFrame = NDArray[Any]
-Mask = NDArray[Any]
-Points = NDArray[Any]
-Distance = NDArray[Any]
-Matrix = NDArray[Any]
-Anchors = NDArray[Any]
-Translation = NDArray[Any]
+VisionFrame : TypeAlias = NDArray[Any]
+Mask : TypeAlias = NDArray[Any]
+Points : TypeAlias = NDArray[Any]
+Distance : TypeAlias = NDArray[Any]
+Matrix : TypeAlias = NDArray[Any]
+Anchors : TypeAlias = NDArray[Any]
+Translation : TypeAlias = NDArray[Any]
 
-AudioBuffer = bytes
-Audio = NDArray[Any]
-AudioChunk = NDArray[Any]
-AudioFrame = NDArray[Any]
-Spectrogram = NDArray[Any]
-Mel = NDArray[Any]
-MelFilterBank = NDArray[Any]
+AudioBuffer : TypeAlias = bytes
+Audio : TypeAlias = NDArray[Any]
+AudioChunk : TypeAlias = NDArray[Any]
+AudioFrame : TypeAlias = NDArray[Any]
+Spectrogram : TypeAlias = NDArray[Any]
+Mel : TypeAlias = NDArray[Any]
+MelFilterBank : TypeAlias = NDArray[Any]
 
-Fps = float
-Padding = Tuple[int, int, int, int]
+Fps : TypeAlias = float
+Duration : TypeAlias = float
+Padding : TypeAlias = Tuple[int, int, int, int]
 Orientation = Literal['landscape', 'portrait']
-Resolution = Tuple[int, int]
+Resolution : TypeAlias = Tuple[int, int]
 
 ProcessState = Literal['checking', 'processing', 'stopping', 'pending']
 QueuePayload = TypedDict('QueuePayload',
@@ -77,52 +80,79 @@ QueuePayload = TypedDict('QueuePayload',
 	'frame_number' : int,
 	'frame_path' : str
 })
-Args = Dict[str, Any]
-UpdateProgress = Callable[[int], None]
-ProcessFrames = Callable[[List[str], List[QueuePayload], UpdateProgress], None]
-ProcessStep = Callable[[str, int, Args], bool]
+Args : TypeAlias = Dict[str, Any]
+UpdateProgress : TypeAlias = Callable[[int], None]
+ProcessFrames : TypeAlias = Callable[[List[str], List[QueuePayload], UpdateProgress], None]
+ProcessStep : TypeAlias = Callable[[str, int, Args], bool]
 
-Content = Dict[str, Any]
+Content : TypeAlias = Dict[str, Any]
 
-WarpTemplate = Literal['arcface_112_v1', 'arcface_112_v2', 'arcface_128_v2', 'ffhq_512']
-WarpTemplateSet = Dict[WarpTemplate, NDArray[Any]]
+Commands : TypeAlias = List[str]
+
+WarpTemplate = Literal['arcface_112_v1', 'arcface_112_v2', 'arcface_128', 'dfl_whole_face', 'ffhq_512', 'mtcnn_512', 'styleganex_384']
+WarpTemplateSet : TypeAlias = Dict[WarpTemplate, NDArray[Any]]
 ProcessMode = Literal['output', 'preview', 'stream']
 
 ErrorCode = Literal[0, 1, 2, 3, 4]
 LogLevel = Literal['error', 'warn', 'info', 'debug']
-LogLevelSet = Dict[LogLevel, int]
+LogLevelSet : TypeAlias = Dict[LogLevel, int]
 
 TableHeaders = List[str]
 TableContents = List[List[Any]]
 
-VideoMemoryStrategy = Literal['strict', 'moderate', 'tolerant']
-FaceDetectorModel = Literal['many', 'retinaface', 'scrfd', 'yoloface']
+FaceDetectorModel = Literal['many', 'retinaface', 'scrfd', 'yolo_face']
 FaceLandmarkerModel = Literal['many', '2dfan4', 'peppa_wutz']
-FaceDetectorSet = Dict[FaceDetectorModel, List[str]]
+FaceDetectorSet : TypeAlias = Dict[FaceDetectorModel, List[str]]
 FaceSelectorMode = Literal['many', 'one', 'reference']
 FaceSelectorOrder = Literal['left-right', 'right-left', 'top-bottom', 'bottom-top', 'small-large', 'large-small', 'best-worst', 'worst-best']
-FaceMaskType = Literal['box', 'occlusion', 'region']
+FaceOccluderModel = Literal['xseg_1', 'xseg_2', 'xseg_3']
+FaceParserModel = Literal['bisenet_resnet_18', 'bisenet_resnet_34']
+FaceMaskType = Literal['box', 'occlusion', 'area', 'region']
+FaceMaskArea = Literal['upper-face', 'lower-face', 'mouth']
 FaceMaskRegion = Literal['skin', 'left-eyebrow', 'right-eyebrow', 'left-eye', 'right-eye', 'glasses', 'nose', 'mouth', 'upper-lip', 'lower-lip']
-TempFrameFormat = Literal['jpg', 'png', 'bmp']
-OutputAudioEncoder = Literal['aac', 'libmp3lame', 'libopus', 'libvorbis']
-OutputVideoEncoder = Literal['libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf', 'h264_videotoolbox', 'hevc_videotoolbox']
-OutputVideoPreset = Literal['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow']
+FaceMaskRegionSet : TypeAlias = Dict[FaceMaskRegion, int]
+FaceMaskAreaSet : TypeAlias = Dict[FaceMaskArea, List[int]]
 
-Download = TypedDict('Download',
+AudioFormat = Literal['flac', 'm4a', 'mp3', 'ogg', 'opus', 'wav']
+ImageFormat = Literal['bmp', 'jpeg', 'png', 'tiff', 'webp']
+VideoFormat = Literal['avi', 'm4v', 'mkv', 'mov', 'mp4', 'webm']
+TempFrameFormat = Literal['bmp', 'jpeg', 'png', 'tiff']
+AudioTypeSet : TypeAlias = Dict[AudioFormat, str]
+ImageTypeSet : TypeAlias = Dict[ImageFormat, str]
+VideoTypeSet : TypeAlias = Dict[VideoFormat, str]
+
+AudioEncoder = Literal['flac', 'aac', 'libmp3lame', 'libopus', 'libvorbis', 'pcm_s16le', 'pcm_s32le']
+VideoEncoder = Literal['libx264', 'libx265', 'libvpx-vp9', 'h264_nvenc', 'hevc_nvenc', 'h264_amf', 'hevc_amf', 'h264_qsv', 'hevc_qsv', 'h264_videotoolbox', 'hevc_videotoolbox', 'rawvideo']
+EncoderSet = TypedDict('EncoderSet',
 {
-	'url' : str,
-	'path' : str
+	'audio' : List[AudioEncoder],
+	'video' : List[VideoEncoder]
 })
-DownloadSet = Dict[str, Download]
+VideoPreset = Literal['ultrafast', 'superfast', 'veryfast', 'faster', 'fast', 'medium', 'slow', 'slower', 'veryslow']
 
-ModelOptions = Dict[str, Any]
-ModelSet = Dict[str, ModelOptions]
-ModelInitializer = NDArray[Any]
+BenchmarkResolution = Literal['240p', '360p', '540p', '720p', '1080p', '1440p', '2160p']
+BenchmarkSet : TypeAlias = Dict[BenchmarkResolution, str]
+BenchmarkCycleSet = TypedDict('BenchmarkCycleSet',
+{
+	'target_path' : str,
+	'cycle_count' : int,
+	'average_run' : float,
+	'fastest_run' : float,
+	'slowest_run' : float,
+	'relative_fps' : float
+})
 
-ExecutionProviderKey = Literal['cpu', 'coreml', 'cuda', 'directml', 'openvino', 'rocm', 'tensorrt']
+WebcamMode = Literal['inline', 'udp', 'v4l2']
+StreamMode = Literal['udp', 'v4l2']
+
+ModelOptions : TypeAlias = Dict[str, Any]
+ModelSet : TypeAlias = Dict[str, ModelOptions]
+ModelInitializer : TypeAlias = NDArray[Any]
+
+ExecutionProvider = Literal['cpu', 'coreml', 'cuda', 'directml', 'openvino', 'rocm', 'tensorrt']
 ExecutionProviderValue = Literal['CPUExecutionProvider', 'CoreMLExecutionProvider', 'CUDAExecutionProvider', 'DmlExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'TensorrtExecutionProvider']
-ExecutionProviderSet = Dict[ExecutionProviderKey, ExecutionProviderValue]
-
+ExecutionProviderSet : TypeAlias = Dict[ExecutionProvider, ExecutionProviderValue]
+InferenceSessionProvider : TypeAlias = Any
 ValueAndUnit = TypedDict('ValueAndUnit',
 {
 	'value' : int,
@@ -140,13 +170,18 @@ ExecutionDeviceProduct = TypedDict('ExecutionDeviceProduct',
 })
 ExecutionDeviceVideoMemory = TypedDict('ExecutionDeviceVideoMemory',
 {
-	'total' : ValueAndUnit,
-	'free' : ValueAndUnit
+	'total' : Optional[ValueAndUnit],
+	'free' : Optional[ValueAndUnit]
+})
+ExecutionDeviceTemperature = TypedDict('ExecutionDeviceTemperature',
+{
+	'gpu' : Optional[ValueAndUnit],
+	'memory' : Optional[ValueAndUnit]
 })
 ExecutionDeviceUtilization = TypedDict('ExecutionDeviceUtilization',
 {
-	'gpu' : ValueAndUnit,
-	'memory' : ValueAndUnit
+	'gpu' : Optional[ValueAndUnit],
+	'memory' : Optional[ValueAndUnit]
 })
 ExecutionDevice = TypedDict('ExecutionDevice',
 {
@@ -154,13 +189,30 @@ ExecutionDevice = TypedDict('ExecutionDevice',
 	'framework' : ExecutionDeviceFramework,
 	'product' : ExecutionDeviceProduct,
 	'video_memory' : ExecutionDeviceVideoMemory,
+	'temperature': ExecutionDeviceTemperature,
 	'utilization' : ExecutionDeviceUtilization
 })
 
+DownloadProvider = Literal['github', 'huggingface']
+DownloadProviderValue = TypedDict('DownloadProviderValue',
+{
+	'urls' : List[str],
+	'path' : str
+})
+DownloadProviderSet : TypeAlias = Dict[DownloadProvider, DownloadProviderValue]
+DownloadScope = Literal['lite', 'full']
+Download = TypedDict('Download',
+{
+	'url' : str,
+	'path' : str
+})
+DownloadSet : TypeAlias = Dict[str, Download]
+
+VideoMemoryStrategy = Literal['strict', 'moderate', 'tolerant']
 AppContext = Literal['cli', 'ui']
 
-InferencePool = Dict[str, InferenceSession]
-InferencePoolSet = Dict[AppContext, Dict[str, InferencePool]]
+InferencePool : TypeAlias = Dict[str, InferenceSession]
+InferencePoolSet : TypeAlias = Dict[AppContext, Dict[str, InferencePool]]
 
 UiWorkflow = Literal['instant_runner', 'job_runner', 'job_manager']
 
@@ -169,7 +221,7 @@ JobStore = TypedDict('JobStore',
 	'job_keys' : List[str],
 	'step_keys' : List[str]
 })
-JobOutputSet = Dict[str, List[str]]
+JobOutputSet : TypeAlias = Dict[str, List[str]]
 JobStatus = Literal['drafted', 'queued', 'completed', 'failed']
 JobStepStatus = Literal['drafted', 'queued', 'started', 'completed', 'failed']
 JobStep = TypedDict('JobStep',
@@ -184,17 +236,24 @@ Job = TypedDict('Job',
 	'date_updated' : Optional[str],
 	'steps' : List[JobStep]
 })
-JobSet = Dict[str, Job]
+JobSet : TypeAlias = Dict[str, Job]
 
-ApplyStateItem = Callable[[Any, Any], None]
 StateKey = Literal\
 [
 	'command',
 	'config_path',
+	'temp_path',
 	'jobs_path',
 	'source_paths',
 	'target_path',
 	'output_path',
+	'source_pattern',
+	'target_pattern',
+	'output_pattern',
+	'download_providers',
+	'download_scope',
+	'benchmark_resolutions',
+	'benchmark_cycle_count',
 	'face_detector_model',
 	'face_detector_size',
 	'face_detector_angles',
@@ -210,10 +269,13 @@ StateKey = Literal\
 	'reference_face_position',
 	'reference_face_distance',
 	'reference_frame_number',
+	'face_occluder_model',
+	'face_parser_model',
 	'face_mask_types',
+	'face_mask_areas',
+	'face_mask_regions',
 	'face_mask_blur',
 	'face_mask_padding',
-	'face_mask_regions',
 	'trim_frame_start',
 	'trim_frame_end',
 	'temp_frame_format',
@@ -221,12 +283,13 @@ StateKey = Literal\
 	'output_image_quality',
 	'output_image_resolution',
 	'output_audio_encoder',
+	'output_audio_quality',
+	'output_audio_volume',
 	'output_video_encoder',
 	'output_video_preset',
 	'output_video_quality',
 	'output_video_resolution',
 	'output_video_fps',
-	'skip_audio',
 	'processors',
 	'open_browser',
 	'ui_layouts',
@@ -237,8 +300,8 @@ StateKey = Literal\
 	'execution_queue_count',
 	'video_memory_strategy',
 	'system_memory_limit',
-	'skip_download',
 	'log_level',
+	'halt_on_error',
 	'job_id',
 	'job_status',
 	'step_index'
@@ -247,10 +310,18 @@ State = TypedDict('State',
 {
 	'command' : str,
 	'config_path' : str,
+	'temp_path' : str,
 	'jobs_path' : str,
 	'source_paths' : List[str],
 	'target_path' : str,
 	'output_path' : str,
+	'source_pattern' : str,
+	'target_pattern' : str,
+	'output_pattern' : str,
+	'download_providers': List[DownloadProvider],
+	'download_scope': DownloadScope,
+	'benchmark_resolutions': List[BenchmarkResolution],
+	'benchmark_cycle_count': int,
 	'face_detector_model' : FaceDetectorModel,
 	'face_detector_size' : str,
 	'face_detector_angles' : List[Angle],
@@ -266,37 +337,43 @@ State = TypedDict('State',
 	'reference_face_position' : int,
 	'reference_face_distance' : float,
 	'reference_frame_number' : int,
+	'face_occluder_model' : FaceOccluderModel,
+	'face_parser_model' : FaceParserModel,
 	'face_mask_types' : List[FaceMaskType],
+	'face_mask_areas' : List[FaceMaskArea],
+	'face_mask_regions' : List[FaceMaskRegion],
 	'face_mask_blur' : float,
 	'face_mask_padding' : Padding,
-	'face_mask_regions' : List[FaceMaskRegion],
 	'trim_frame_start' : int,
 	'trim_frame_end' : int,
 	'temp_frame_format' : TempFrameFormat,
 	'keep_temp' : bool,
 	'output_image_quality' : int,
 	'output_image_resolution' : str,
-	'output_audio_encoder' : OutputAudioEncoder,
-	'output_video_encoder' : OutputVideoEncoder,
-	'output_video_preset' : OutputVideoPreset,
+	'output_audio_encoder' : AudioEncoder,
+	'output_audio_quality' : int,
+	'output_audio_volume' : int,
+	'output_video_encoder' : VideoEncoder,
+	'output_video_preset' : VideoPreset,
 	'output_video_quality' : int,
 	'output_video_resolution' : str,
 	'output_video_fps' : float,
-	'skip_audio' : bool,
 	'processors' : List[str],
 	'open_browser' : bool,
 	'ui_layouts' : List[str],
 	'ui_workflow' : UiWorkflow,
 	'execution_device_id' : str,
-	'execution_providers' : List[ExecutionProviderKey],
+	'execution_providers' : List[ExecutionProvider],
 	'execution_thread_count' : int,
 	'execution_queue_count' : int,
 	'video_memory_strategy' : VideoMemoryStrategy,
 	'system_memory_limit' : int,
-	'skip_download' : bool,
 	'log_level' : LogLevel,
+	'halt_on_error' : bool,
 	'job_id' : str,
 	'job_status' : JobStatus,
 	'step_index' : int
 })
-StateSet = Dict[AppContext, State]
+ApplyStateItem : TypeAlias = Callable[[Any, Any], None]
+StateSet : TypeAlias = Dict[AppContext, State]
+

facefusion/uis/assets/overrides.css

@@ -1,12 +1,38 @@
 :root:root:root:root .gradio-container
 {
-	max-width: 110em;
 	overflow: unset;
 }
 
+:root:root:root:root main
+{
+	max-width: 110em;
+}
+
 :root:root:root:root input[type="number"]
 {
-	max-width: 6rem;
+	appearance: textfield;
+	border-radius: unset;
+	text-align: center;
+	order: 1;
+	padding: unset
+}
+
+:root:root:root:root input[type="number"]::-webkit-inner-spin-button
+{
+	appearance: none;
+}
+
+:root:root:root:root input[type="number"]:focus
+{
+	outline: unset;
+}
+
+:root:root:root:root .reset-button
+{
+	background: var(--background-fill-secondary);
+	border: unset;
+	font-size: unset;
+	padding: unset;
 }
 
 :root:root:root:root [type="checkbox"],
@@ -17,39 +43,25 @@
 	width: 1.125rem;
 }
 
-:root:root:root:root input[type="range"],
-:root:root:root:root .range-slider div
+:root:root:root:root input[type="range"]
 {
-	height: 0.5rem;
-	border-radius: 0.5rem;
+	background: transparent;
 }
 
 :root:root:root:root input[type="range"]::-moz-range-thumb,
 :root:root:root:root input[type="range"]::-webkit-slider-thumb
 {
 	background: var(--neutral-300);
-	border: unset;
+	box-shadow: unset;
 	border-radius: 50%;
 	height: 1.125rem;
 	width: 1.125rem;
 }
 
-:root:root:root:root input[type="range"]::-webkit-slider-thumb
+:root:root:root:root .thumbnail-item
 {
-	margin-top: 0.375rem;
-}
-
-:root:root:root:root .range-slider input[type="range"]::-webkit-slider-thumb
-{
-	margin-top: 0.125rem;
-}
-
-:root:root:root:root .range-slider div,
-:root:root:root:root .range-slider input[type="range"]
-{
-	bottom: 50%;
-	margin-top: -0.25rem;
-	top: 50%;
+	border: unset;
+	box-shadow: unset;
 }
 
 :root:root:root:root .grid-wrap.fixed-height
@@ -57,27 +69,67 @@
 	min-height: unset;
 }
 
-:root:root:root:root .generating,
-:root:root:root:root .thumbnail-item
+:root:root:root:root .box-face-selector .empty,
+:root:root:root:root .box-face-selector .gallery-container
 {
-	border: unset;
+	min-height: 7.375rem;
 }
 
+:root:root:root:root .tab-wrapper
+{
+	padding: 0 0.625rem;
+}
+
+:root:root:root:root .tab-container
+{
+	gap: 0.5em;
+}
+
+:root:root:root:root .tab-container button
+{
+	background: unset;
+	border-bottom: 0.125rem solid;
+}
+
+:root:root:root:root .tab-container button.selected
+{
+	color: var(--primary-500)
+}
+
+:root:root:root:root .toast-body
+{
+	background: white;
+	color: var(--primary-500);
+	border: unset;
+	border-radius: unset;
+}
+
+:root:root:root:root .dark .toast-body
+{
+	background: var(--neutral-900);
+	color: var(--primary-600);
+}
+
+:root:root:root:root .toast-icon,
+:root:root:root:root .toast-title,
+:root:root:root:root .toast-text,
+:root:root:root:root .toast-close
+{
+	color: unset;
+}
+
+:root:root:root:root .toast-body .timer
+{
+	background: currentColor;
+}
+
+:root:root:root:root .slider_input_container > span,
 :root:root:root:root .feather-upload,
 :root:root:root:root footer
 {
 	display: none;
 }
 
-:root:root:root:root .tab-nav > button
-{
-	border: unset;
-	box-shadow: 0 0.125rem;
-	font-size: 1.125em;
-	margin: 0.5rem 0.75rem;
-	padding: unset;
-}
-
 :root:root:root:root .image-frame
 {
 	width: 100%;
@@ -94,3 +146,11 @@
 	top: 0;
 	z-index: 100;
 }
+
+:root:root:root:root .block .error
+{
+	border: 0.125rem solid;
+	padding: 0.375rem 0.75rem;
+	font-size: 0.75rem;
+	text-transform: uppercase;
+}

facefusion/uis/choices.py

@@ -1,11 +1,9 @@
 from typing import List
 
-from facefusion.uis.typing import JobManagerAction, JobRunnerAction, WebcamMode
+from facefusion.uis.types import JobManagerAction, JobRunnerAction
 
 job_manager_actions : List[JobManagerAction] = [ 'job-create', 'job-submit', 'job-delete', 'job-add-step', 'job-remix-step', 'job-insert-step', 'job-remove-step' ]
 job_runner_actions : List[JobRunnerAction] = [ 'job-run', 'job-run-all', 'job-retry', 'job-retry-all' ]
 
-common_options : List[str] = [ 'keep-temp', 'skip-audio', 'skip-download' ]
+common_options : List[str] = [ 'keep-temp' ]
 
-webcam_modes : List[WebcamMode] = [ 'inline', 'udp', 'v4l2' ]
-webcam_resolutions : List[str] = [ '320x240', '640x480', '800x600', '1024x768', '1280x720', '1280x960', '1920x1080', '2560x1440', '3840x2160' ]

facefusion/uis/components/age_modifier_options.py

@@ -6,7 +6,7 @@ from facefusion import state_manager, wording
 from facefusion.common_helper import calc_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import AgeModifierModel
+from facefusion.processors.types import AgeModifierModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 AGE_MODIFIER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -17,11 +17,12 @@ def render() -> None:
 	global AGE_MODIFIER_MODEL_DROPDOWN
 	global AGE_MODIFIER_DIRECTION_SLIDER
 
+	has_age_modifier = 'age_modifier' in state_manager.get_item('processors')
 	AGE_MODIFIER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.age_modifier_model_dropdown'),
 		choices = processors_choices.age_modifier_models,
 		value = state_manager.get_item('age_modifier_model'),
-		visible = 'age_modifier' in state_manager.get_item('processors')
+		visible = has_age_modifier
 	)
 	AGE_MODIFIER_DIRECTION_SLIDER = gradio.Slider(
 		label = wording.get('uis.age_modifier_direction_slider'),
@@ -29,7 +30,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.age_modifier_direction_range),
 		minimum = processors_choices.age_modifier_direction_range[0],
 		maximum = processors_choices.age_modifier_direction_range[-1],
-		visible = 'age_modifier' in state_manager.get_item('processors')
+		visible = has_age_modifier
 	)
 	register_ui_component('age_modifier_model_dropdown', AGE_MODIFIER_MODEL_DROPDOWN)
 	register_ui_component('age_modifier_direction_slider', AGE_MODIFIER_DIRECTION_SLIDER)

facefusion/uis/components/benchmark.py

@@ -1,44 +1,24 @@
-import hashlib
-import os
-import statistics
-import tempfile
-from time import perf_counter
-from typing import Any, Dict, Generator, List, Optional
+from typing import Any, Generator, List, Optional
 
 import gradio
 
-from facefusion import state_manager, wording
-from facefusion.core import conditional_process
-from facefusion.filesystem import is_video
-from facefusion.memory import limit_system_memory
+from facefusion import benchmarker, state_manager, wording
+from facefusion.types import BenchmarkResolution
 from facefusion.uis.core import get_ui_component
-from facefusion.vision import count_video_frame_total, detect_video_fps, detect_video_resolution, pack_resolution
 
 BENCHMARK_BENCHMARKS_DATAFRAME : Optional[gradio.Dataframe] = None
 BENCHMARK_START_BUTTON : Optional[gradio.Button] = None
-BENCHMARK_CLEAR_BUTTON : Optional[gradio.Button] = None
-BENCHMARKS : Dict[str, str] =\
-{
-	'240p': '.assets/examples/target-240p.mp4',
-	'360p': '.assets/examples/target-360p.mp4',
-	'540p': '.assets/examples/target-540p.mp4',
-	'720p': '.assets/examples/target-720p.mp4',
-	'1080p': '.assets/examples/target-1080p.mp4',
-	'1440p': '.assets/examples/target-1440p.mp4',
-	'2160p': '.assets/examples/target-2160p.mp4'
-}
 
 
 def render() -> None:
 	global BENCHMARK_BENCHMARKS_DATAFRAME
 	global BENCHMARK_START_BUTTON
-	global BENCHMARK_CLEAR_BUTTON
 
 	BENCHMARK_BENCHMARKS_DATAFRAME = gradio.Dataframe(
 		headers =
 		[
 			'target_path',
-			'benchmark_cycles',
+			'cycle_count',
 			'average_run',
 			'fastest_run',
 			'slowest_run',
@@ -63,72 +43,19 @@ def render() -> None:
 
 
 def listen() -> None:
-	benchmark_runs_checkbox_group = get_ui_component('benchmark_runs_checkbox_group')
-	benchmark_cycles_slider = get_ui_component('benchmark_cycles_slider')
+	benchmark_resolutions_checkbox_group = get_ui_component('benchmark_resolutions_checkbox_group')
+	benchmark_cycle_count_slider = get_ui_component('benchmark_cycle_count_slider')
 
-	if benchmark_runs_checkbox_group and benchmark_cycles_slider:
-		BENCHMARK_START_BUTTON.click(start, inputs = [ benchmark_runs_checkbox_group, benchmark_cycles_slider ], outputs = BENCHMARK_BENCHMARKS_DATAFRAME)
+	if benchmark_resolutions_checkbox_group and benchmark_cycle_count_slider:
+		BENCHMARK_START_BUTTON.click(start, inputs = [ benchmark_resolutions_checkbox_group, benchmark_cycle_count_slider ], outputs = BENCHMARK_BENCHMARKS_DATAFRAME)
 
 
-def suggest_output_path(target_path : str) -> Optional[str]:
-	if is_video(target_path):
-		_, target_extension = os.path.splitext(target_path)
-		return os.path.join(tempfile.gettempdir(), hashlib.sha1().hexdigest()[:8] + target_extension)
-	return None
-
-
-def start(benchmark_runs : List[str], benchmark_cycles : int) -> Generator[List[Any], None, None]:
-	state_manager.init_item('source_paths', [ '.assets/examples/source.jpg', '.assets/examples/source.mp3' ])
-	state_manager.init_item('face_landmarker_score', 0)
-	state_manager.init_item('temp_frame_format', 'bmp')
-	state_manager.init_item('output_video_preset', 'ultrafast')
-	state_manager.init_item('skip_audio', True)
+def start(benchmark_resolutions : List[BenchmarkResolution], benchmark_cycle_count : int) -> Generator[List[Any], None, None]:
+	state_manager.set_item('benchmark_resolutions', benchmark_resolutions)
+	state_manager.set_item('benchmark_cycle_count', benchmark_cycle_count)
 	state_manager.sync_item('execution_providers')
 	state_manager.sync_item('execution_thread_count')
 	state_manager.sync_item('execution_queue_count')
-	state_manager.sync_item('system_memory_limit')
-	benchmark_results = []
-	target_paths = [ BENCHMARKS[benchmark_run] for benchmark_run in benchmark_runs if benchmark_run in BENCHMARKS ]
 
-	if target_paths:
-		pre_process()
-		for target_path in target_paths:
-			state_manager.init_item('target_path', target_path)
-			state_manager.init_item('output_path', suggest_output_path(state_manager.get_item('target_path')))
-			benchmark_results.append(benchmark(benchmark_cycles))
-			yield benchmark_results
-
-
-def pre_process() -> None:
-	system_memory_limit = state_manager.get_item('system_memory_limit')
-	if system_memory_limit and system_memory_limit > 0:
-		limit_system_memory(system_memory_limit)
-
-
-def benchmark(benchmark_cycles : int) -> List[Any]:
-	process_times = []
-	video_frame_total = count_video_frame_total(state_manager.get_item('target_path'))
-	output_video_resolution = detect_video_resolution(state_manager.get_item('target_path'))
-	state_manager.init_item('output_video_resolution', pack_resolution(output_video_resolution))
-	state_manager.init_item('output_video_fps', detect_video_fps(state_manager.get_item('target_path')))
-
-	conditional_process()
-	for index in range(benchmark_cycles):
-		start_time = perf_counter()
-		conditional_process()
-		end_time = perf_counter()
-		process_times.append(end_time - start_time)
-	average_run = round(statistics.mean(process_times), 2)
-	fastest_run = round(min(process_times), 2)
-	slowest_run = round(max(process_times), 2)
-	relative_fps = round(video_frame_total * benchmark_cycles / sum(process_times), 2)
-
-	return\
-	[
-		state_manager.get_item('target_path'),
-		benchmark_cycles,
-		average_run,
-		fastest_run,
-		slowest_run,
-		relative_fps
-	]
+	for benchmark in benchmarker.run():
+		yield [ list(benchmark_set.values()) for benchmark_set in benchmark ]

facefusion/uis/components/benchmark_options.py

@@ -2,29 +2,29 @@ from typing import Optional
 
 import gradio
 
+import facefusion.choices
 from facefusion import wording
-from facefusion.uis.components.benchmark import BENCHMARKS
 from facefusion.uis.core import register_ui_component
 
-BENCHMARK_RUNS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
-BENCHMARK_CYCLES_SLIDER : Optional[gradio.Button] = None
+BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
+BENCHMARK_CYCLE_COUNT_SLIDER : Optional[gradio.Button] = None
 
 
 def render() -> None:
-	global BENCHMARK_RUNS_CHECKBOX_GROUP
-	global BENCHMARK_CYCLES_SLIDER
+	global BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP
+	global BENCHMARK_CYCLE_COUNT_SLIDER
 
-	BENCHMARK_RUNS_CHECKBOX_GROUP = gradio.CheckboxGroup(
-		label = wording.get('uis.benchmark_runs_checkbox_group'),
-		value = list(BENCHMARKS.keys()),
-		choices = list(BENCHMARKS.keys())
+	BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP = gradio.CheckboxGroup(
+		label = wording.get('uis.benchmark_resolutions_checkbox_group'),
+		choices = facefusion.choices.benchmark_resolutions,
+		value = facefusion.choices.benchmark_resolutions
 	)
-	BENCHMARK_CYCLES_SLIDER = gradio.Slider(
-		label = wording.get('uis.benchmark_cycles_slider'),
+	BENCHMARK_CYCLE_COUNT_SLIDER = gradio.Slider(
+		label = wording.get('uis.benchmark_cycle_count_slider'),
 		value = 5,
 		step = 1,
-		minimum = 1,
-		maximum = 10
+		minimum = min(facefusion.choices.benchmark_cycle_count_range),
+		maximum = max(facefusion.choices.benchmark_cycle_count_range)
 	)
-	register_ui_component('benchmark_runs_checkbox_group', BENCHMARK_RUNS_CHECKBOX_GROUP)
-	register_ui_component('benchmark_cycles_slider', BENCHMARK_CYCLES_SLIDER)
+	register_ui_component('benchmark_resolutions_checkbox_group', BENCHMARK_RESOLUTIONS_CHECKBOX_GROUP)
+	register_ui_component('benchmark_cycle_count_slider', BENCHMARK_CYCLE_COUNT_SLIDER)

facefusion/uis/components/common_options.py

@@ -13,12 +13,8 @@ def render() -> None:
 
 	common_options = []
 
-	if state_manager.get_item('skip_download'):
-		common_options.append('skip-download')
 	if state_manager.get_item('keep_temp'):
 		common_options.append('keep-temp')
-	if state_manager.get_item('skip_audio'):
-		common_options.append('skip-audio')
 
 	COMMON_OPTIONS_CHECKBOX_GROUP = gradio.Checkboxgroup(
 		label = wording.get('uis.common_options_checkbox_group'),
@@ -32,9 +28,5 @@ def listen() -> None:
 
 
 def update(common_options : List[str]) -> None:
-	skip_temp = 'skip-download' in common_options
 	keep_temp = 'keep-temp' in common_options
-	skip_audio = 'skip-audio' in common_options
-	state_manager.set_item('skip_download', skip_temp)
 	state_manager.set_item('keep_temp', keep_temp)
-	state_manager.set_item('skip_audio', skip_audio)

facefusion/uis/components/deep_swapper_options.py

@@ -0,0 +1,64 @@
+from typing import List, Optional, Tuple
+
+import gradio
+
+from facefusion import state_manager, wording
+from facefusion.common_helper import calc_int_step
+from facefusion.processors import choices as processors_choices
+from facefusion.processors.core import load_processor_module
+from facefusion.processors.types import DeepSwapperModel
+from facefusion.uis.core import get_ui_component, register_ui_component
+
+DEEP_SWAPPER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
+DEEP_SWAPPER_MORPH_SLIDER : Optional[gradio.Slider] = None
+
+
+def render() -> None:
+	global DEEP_SWAPPER_MODEL_DROPDOWN
+	global DEEP_SWAPPER_MORPH_SLIDER
+
+	has_deep_swapper = 'deep_swapper' in state_manager.get_item('processors')
+	DEEP_SWAPPER_MODEL_DROPDOWN = gradio.Dropdown(
+		label = wording.get('uis.deep_swapper_model_dropdown'),
+		choices = processors_choices.deep_swapper_models,
+		value = state_manager.get_item('deep_swapper_model'),
+		visible = has_deep_swapper
+	)
+	DEEP_SWAPPER_MORPH_SLIDER = gradio.Slider(
+		label = wording.get('uis.deep_swapper_morph_slider'),
+		value = state_manager.get_item('deep_swapper_morph'),
+		step = calc_int_step(processors_choices.deep_swapper_morph_range),
+		minimum = processors_choices.deep_swapper_morph_range[0],
+		maximum = processors_choices.deep_swapper_morph_range[-1],
+		visible = has_deep_swapper and load_processor_module('deep_swapper').get_inference_pool() and load_processor_module('deep_swapper').has_morph_input()
+	)
+	register_ui_component('deep_swapper_model_dropdown', DEEP_SWAPPER_MODEL_DROPDOWN)
+	register_ui_component('deep_swapper_morph_slider', DEEP_SWAPPER_MORPH_SLIDER)
+
+
+def listen() -> None:
+	DEEP_SWAPPER_MODEL_DROPDOWN.change(update_deep_swapper_model, inputs = DEEP_SWAPPER_MODEL_DROPDOWN, outputs = [ DEEP_SWAPPER_MODEL_DROPDOWN, DEEP_SWAPPER_MORPH_SLIDER ])
+	DEEP_SWAPPER_MORPH_SLIDER.release(update_deep_swapper_morph, inputs = DEEP_SWAPPER_MORPH_SLIDER)
+
+	processors_checkbox_group = get_ui_component('processors_checkbox_group')
+	if processors_checkbox_group:
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ DEEP_SWAPPER_MODEL_DROPDOWN, DEEP_SWAPPER_MORPH_SLIDER ])
+
+
+def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider]:
+	has_deep_swapper = 'deep_swapper' in processors
+	return gradio.Dropdown(visible = has_deep_swapper), gradio.Slider(visible = has_deep_swapper and load_processor_module('deep_swapper').get_inference_pool() and load_processor_module('deep_swapper').has_morph_input())
+
+
+def update_deep_swapper_model(deep_swapper_model : DeepSwapperModel) -> Tuple[gradio.Dropdown, gradio.Slider]:
+	deep_swapper_module = load_processor_module('deep_swapper')
+	deep_swapper_module.clear_inference_pool()
+	state_manager.set_item('deep_swapper_model', deep_swapper_model)
+
+	if deep_swapper_module.pre_check():
+		return gradio.Dropdown(value = state_manager.get_item('deep_swapper_model')), gradio.Slider(visible = deep_swapper_module.has_morph_input())
+	return gradio.Dropdown(), gradio.Slider()
+
+
+def update_deep_swapper_morph(deep_swapper_morph : int) -> None:
+	state_manager.set_item('deep_swapper_morph', deep_swapper_morph)

facefusion/uis/components/download.py

@@ -0,0 +1,48 @@
+from typing import List, Optional
+
+import gradio
+
+import facefusion.choices
+from facefusion import content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, state_manager, voice_extractor, wording
+from facefusion.filesystem import get_file_name, resolve_file_paths
+from facefusion.processors.core import get_processors_modules
+from facefusion.types import DownloadProvider
+
+DOWNLOAD_PROVIDERS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
+
+
+def render() -> None:
+	global DOWNLOAD_PROVIDERS_CHECKBOX_GROUP
+
+	DOWNLOAD_PROVIDERS_CHECKBOX_GROUP = gradio.CheckboxGroup(
+		label = wording.get('uis.download_providers_checkbox_group'),
+		choices = facefusion.choices.download_providers,
+		value = state_manager.get_item('download_providers')
+	)
+
+
+def listen() -> None:
+	DOWNLOAD_PROVIDERS_CHECKBOX_GROUP.change(update_download_providers, inputs = DOWNLOAD_PROVIDERS_CHECKBOX_GROUP, outputs = DOWNLOAD_PROVIDERS_CHECKBOX_GROUP)
+
+
+def update_download_providers(download_providers : List[DownloadProvider]) -> gradio.CheckboxGroup:
+	common_modules =\
+	[
+		content_analyser,
+		face_classifier,
+		face_detector,
+		face_landmarker,
+		face_recognizer,
+		face_masker,
+		voice_extractor
+	]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
+	processor_modules = get_processors_modules(available_processors)
+
+	for module in common_modules + processor_modules:
+		if hasattr(module, 'create_static_model_set'):
+			module.create_static_model_set.cache_clear()
+
+	download_providers = download_providers or facefusion.choices.download_providers
+	state_manager.set_item('download_providers', download_providers)
+	return gradio.CheckboxGroup(value = state_manager.get_item('download_providers'))

facefusion/uis/components/execution.py

@@ -3,9 +3,10 @@ from typing import List, Optional
 import gradio
 
 from facefusion import content_analyser, face_classifier, face_detector, face_landmarker, face_masker, face_recognizer, state_manager, voice_extractor, wording
-from facefusion.execution import get_execution_provider_choices
-from facefusion.processors.core import clear_processors_modules
-from facefusion.typing import ExecutionProviderKey
+from facefusion.execution import get_available_execution_providers
+from facefusion.filesystem import get_file_name, resolve_file_paths
+from facefusion.processors.core import get_processors_modules
+from facefusion.types import ExecutionProvider
 
 EXECUTION_PROVIDERS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 
@@ -15,7 +16,7 @@ def render() -> None:
 
 	EXECUTION_PROVIDERS_CHECKBOX_GROUP = gradio.CheckboxGroup(
 		label = wording.get('uis.execution_providers_checkbox_group'),
-		choices = get_execution_provider_choices(),
+		choices = get_available_execution_providers(),
 		value = state_manager.get_item('execution_providers')
 	)
 
@@ -24,15 +25,24 @@ def listen() -> None:
 	EXECUTION_PROVIDERS_CHECKBOX_GROUP.change(update_execution_providers, inputs = EXECUTION_PROVIDERS_CHECKBOX_GROUP, outputs = EXECUTION_PROVIDERS_CHECKBOX_GROUP)
 
 
-def update_execution_providers(execution_providers : List[ExecutionProviderKey]) -> gradio.CheckboxGroup:
-	content_analyser.clear_inference_pool()
-	face_classifier.clear_inference_pool()
-	face_detector.clear_inference_pool()
-	face_landmarker.clear_inference_pool()
-	face_masker.clear_inference_pool()
-	face_recognizer.clear_inference_pool()
-	voice_extractor.clear_inference_pool()
-	clear_processors_modules(state_manager.get_item('processors'))
-	execution_providers = execution_providers or get_execution_provider_choices()
+def update_execution_providers(execution_providers : List[ExecutionProvider]) -> gradio.CheckboxGroup:
+	common_modules =\
+	[
+		content_analyser,
+		face_classifier,
+		face_detector,
+		face_landmarker,
+		face_masker,
+		face_recognizer,
+		voice_extractor
+	]
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
+	processor_modules = get_processors_modules(available_processors)
+
+	for module in common_modules + processor_modules:
+		if hasattr(module, 'clear_inference_pool'):
+			module.clear_inference_pool()
+
+	execution_providers = execution_providers or get_available_execution_providers()
 	state_manager.set_item('execution_providers', execution_providers)
 	return gradio.CheckboxGroup(value = state_manager.get_item('execution_providers'))

facefusion/uis/components/expression_restorer_options.py

@@ -6,7 +6,7 @@ from facefusion import state_manager, wording
 from facefusion.common_helper import calc_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import ExpressionRestorerModel
+from facefusion.processors.types import ExpressionRestorerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 EXPRESSION_RESTORER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -17,11 +17,12 @@ def render() -> None:
 	global EXPRESSION_RESTORER_MODEL_DROPDOWN
 	global EXPRESSION_RESTORER_FACTOR_SLIDER
 
+	has_expression_restorer = 'expression_restorer' in state_manager.get_item('processors')
 	EXPRESSION_RESTORER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.expression_restorer_model_dropdown'),
 		choices = processors_choices.expression_restorer_models,
 		value = state_manager.get_item('expression_restorer_model'),
-		visible = 'expression_restorer' in state_manager.get_item('processors')
+		visible = has_expression_restorer
 	)
 	EXPRESSION_RESTORER_FACTOR_SLIDER = gradio.Slider(
 		label = wording.get('uis.expression_restorer_factor_slider'),
@@ -29,7 +30,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.expression_restorer_factor_range),
 		minimum = processors_choices.expression_restorer_factor_range[0],
 		maximum = processors_choices.expression_restorer_factor_range[-1],
-		visible = 'expression_restorer' in state_manager.get_item('processors'),
+		visible = has_expression_restorer
 	)
 	register_ui_component('expression_restorer_model_dropdown', EXPRESSION_RESTORER_MODEL_DROPDOWN)
 	register_ui_component('expression_restorer_factor_slider', EXPRESSION_RESTORER_FACTOR_SLIDER)

facefusion/uis/components/face_debugger_options.py

@@ -4,7 +4,7 @@ import gradio
 
 from facefusion import state_manager, wording
 from facefusion.processors import choices as processors_choices
-from facefusion.processors.typing import FaceDebuggerItem
+from facefusion.processors.types import FaceDebuggerItem
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
@@ -13,11 +13,12 @@ FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 def render() -> None:
 	global FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP
 
+	has_face_debugger = 'face_debugger' in state_manager.get_item('processors')
 	FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP = gradio.CheckboxGroup(
 		label = wording.get('uis.face_debugger_items_checkbox_group'),
 		choices = processors_choices.face_debugger_items,
 		value = state_manager.get_item('face_debugger_items'),
-		visible = 'face_debugger' in state_manager.get_item('processors')
+		visible = has_face_debugger
 	)
 	register_ui_component('face_debugger_items_checkbox_group', FACE_DEBUGGER_ITEMS_CHECKBOX_GROUP)
 

facefusion/uis/components/face_detector.py

@@ -3,11 +3,11 @@ from typing import Optional, Sequence, Tuple
 import gradio
 
 import facefusion.choices
-from facefusion import choices, face_detector, state_manager, wording
+from facefusion import face_detector, state_manager, wording
 from facefusion.common_helper import calc_float_step, get_last
-from facefusion.typing import Angle, FaceDetectorModel, Score
+from facefusion.types import Angle, FaceDetectorModel, Score
 from facefusion.uis.core import register_ui_component
-from facefusion.uis.typing import ComponentOptions
+from facefusion.uis.types import ComponentOptions
 
 FACE_DETECTOR_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_DETECTOR_SIZE_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -31,7 +31,7 @@ def render() -> None:
 	with gradio.Row():
 		FACE_DETECTOR_MODEL_DROPDOWN = gradio.Dropdown(
 			label = wording.get('uis.face_detector_model_dropdown'),
-			choices = facefusion.choices.face_detector_set.keys(),
+			choices = facefusion.choices.face_detector_models,
 			value = state_manager.get_item('face_detector_model')
 		)
 		FACE_DETECTOR_SIZE_DROPDOWN = gradio.Dropdown(**face_detector_size_dropdown_options)
@@ -65,7 +65,7 @@ def update_face_detector_model(face_detector_model : FaceDetectorModel) -> Tuple
 	state_manager.set_item('face_detector_model', face_detector_model)
 
 	if face_detector.pre_check():
-		face_detector_size_choices = choices.face_detector_set.get(state_manager.get_item('face_detector_model'))
+		face_detector_size_choices = facefusion.choices.face_detector_set.get(state_manager.get_item('face_detector_model'))
 		state_manager.set_item('face_detector_size', get_last(face_detector_size_choices))
 		return gradio.Dropdown(value = state_manager.get_item('face_detector_model')), gradio.Dropdown(value = state_manager.get_item('face_detector_size'), choices = face_detector_size_choices)
 	return gradio.Dropdown(), gradio.Dropdown()

facefusion/uis/components/face_editor_options.py

@@ -6,7 +6,7 @@ from facefusion import state_manager, wording
 from facefusion.common_helper import calc_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FaceEditorModel
+from facefusion.processors.types import FaceEditorModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_EDITOR_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -43,11 +43,12 @@ def render() -> None:
 	global FACE_EDITOR_HEAD_YAW_SLIDER
 	global FACE_EDITOR_HEAD_ROLL_SLIDER
 
+	has_face_editor = 'face_editor' in state_manager.get_item('processors')
 	FACE_EDITOR_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.face_editor_model_dropdown'),
 		choices = processors_choices.face_editor_models,
 		value = state_manager.get_item('face_editor_model'),
-		visible = 'face_editor' in state_manager.get_item('processors')
+		visible = has_face_editor
 	)
 	FACE_EDITOR_EYEBROW_DIRECTION_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eyebrow_direction_slider'),
@@ -55,7 +56,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_eyebrow_direction_range),
 		minimum = processors_choices.face_editor_eyebrow_direction_range[0],
 		maximum = processors_choices.face_editor_eyebrow_direction_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_EYE_GAZE_HORIZONTAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eye_gaze_horizontal_slider'),
@@ -63,7 +64,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_eye_gaze_horizontal_range),
 		minimum = processors_choices.face_editor_eye_gaze_horizontal_range[0],
 		maximum = processors_choices.face_editor_eye_gaze_horizontal_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_EYE_GAZE_VERTICAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eye_gaze_vertical_slider'),
@@ -71,7 +72,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_eye_gaze_vertical_range),
 		minimum = processors_choices.face_editor_eye_gaze_vertical_range[0],
 		maximum = processors_choices.face_editor_eye_gaze_vertical_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_EYE_OPEN_RATIO_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_eye_open_ratio_slider'),
@@ -79,7 +80,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_eye_open_ratio_range),
 		minimum = processors_choices.face_editor_eye_open_ratio_range[0],
 		maximum = processors_choices.face_editor_eye_open_ratio_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_LIP_OPEN_RATIO_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_lip_open_ratio_slider'),
@@ -87,7 +88,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_lip_open_ratio_range),
 		minimum = processors_choices.face_editor_lip_open_ratio_range[0],
 		maximum = processors_choices.face_editor_lip_open_ratio_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_MOUTH_GRIM_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_grim_slider'),
@@ -95,7 +96,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_mouth_grim_range),
 		minimum = processors_choices.face_editor_mouth_grim_range[0],
 		maximum = processors_choices.face_editor_mouth_grim_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_MOUTH_POUT_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_pout_slider'),
@@ -103,7 +104,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_mouth_pout_range),
 		minimum = processors_choices.face_editor_mouth_pout_range[0],
 		maximum = processors_choices.face_editor_mouth_pout_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_MOUTH_PURSE_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_purse_slider'),
@@ -111,7 +112,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_mouth_purse_range),
 		minimum = processors_choices.face_editor_mouth_purse_range[0],
 		maximum = processors_choices.face_editor_mouth_purse_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_MOUTH_SMILE_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_smile_slider'),
@@ -119,7 +120,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_mouth_smile_range),
 		minimum = processors_choices.face_editor_mouth_smile_range[0],
 		maximum = processors_choices.face_editor_mouth_smile_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_MOUTH_POSITION_HORIZONTAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_position_horizontal_slider'),
@@ -127,7 +128,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_mouth_position_horizontal_range),
 		minimum = processors_choices.face_editor_mouth_position_horizontal_range[0],
 		maximum = processors_choices.face_editor_mouth_position_horizontal_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_MOUTH_POSITION_VERTICAL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_mouth_position_vertical_slider'),
@@ -135,7 +136,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_mouth_position_vertical_range),
 		minimum = processors_choices.face_editor_mouth_position_vertical_range[0],
 		maximum = processors_choices.face_editor_mouth_position_vertical_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_HEAD_PITCH_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_head_pitch_slider'),
@@ -143,7 +144,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_head_pitch_range),
 		minimum = processors_choices.face_editor_head_pitch_range[0],
 		maximum = processors_choices.face_editor_head_pitch_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_HEAD_YAW_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_head_yaw_slider'),
@@ -151,7 +152,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_head_yaw_range),
 		minimum = processors_choices.face_editor_head_yaw_range[0],
 		maximum = processors_choices.face_editor_head_yaw_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	FACE_EDITOR_HEAD_ROLL_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_editor_head_roll_slider'),
@@ -159,7 +160,7 @@ def render() -> None:
 		step = calc_float_step(processors_choices.face_editor_head_roll_range),
 		minimum = processors_choices.face_editor_head_roll_range[0],
 		maximum = processors_choices.face_editor_head_roll_range[-1],
-		visible = 'face_editor' in state_manager.get_item('processors'),
+		visible = has_face_editor
 	)
 	register_ui_component('face_editor_model_dropdown', FACE_EDITOR_MODEL_DROPDOWN)
 	register_ui_component('face_editor_eyebrow_direction_slider', FACE_EDITOR_EYEBROW_DIRECTION_SLIDER)
@@ -197,7 +198,7 @@ def listen() -> None:
 
 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [FACE_EDITOR_MODEL_DROPDOWN, FACE_EDITOR_EYEBROW_DIRECTION_SLIDER, FACE_EDITOR_EYE_GAZE_HORIZONTAL_SLIDER, FACE_EDITOR_EYE_GAZE_VERTICAL_SLIDER, FACE_EDITOR_EYE_OPEN_RATIO_SLIDER, FACE_EDITOR_LIP_OPEN_RATIO_SLIDER, FACE_EDITOR_MOUTH_GRIM_SLIDER, FACE_EDITOR_MOUTH_POUT_SLIDER, FACE_EDITOR_MOUTH_PURSE_SLIDER, FACE_EDITOR_MOUTH_SMILE_SLIDER, FACE_EDITOR_MOUTH_POSITION_HORIZONTAL_SLIDER, FACE_EDITOR_MOUTH_POSITION_VERTICAL_SLIDER, FACE_EDITOR_HEAD_PITCH_SLIDER, FACE_EDITOR_HEAD_YAW_SLIDER, FACE_EDITOR_HEAD_ROLL_SLIDER])
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ FACE_EDITOR_MODEL_DROPDOWN, FACE_EDITOR_EYEBROW_DIRECTION_SLIDER, FACE_EDITOR_EYE_GAZE_HORIZONTAL_SLIDER, FACE_EDITOR_EYE_GAZE_VERTICAL_SLIDER, FACE_EDITOR_EYE_OPEN_RATIO_SLIDER, FACE_EDITOR_LIP_OPEN_RATIO_SLIDER, FACE_EDITOR_MOUTH_GRIM_SLIDER, FACE_EDITOR_MOUTH_POUT_SLIDER, FACE_EDITOR_MOUTH_PURSE_SLIDER, FACE_EDITOR_MOUTH_SMILE_SLIDER, FACE_EDITOR_MOUTH_POSITION_HORIZONTAL_SLIDER, FACE_EDITOR_MOUTH_POSITION_VERTICAL_SLIDER, FACE_EDITOR_HEAD_PITCH_SLIDER, FACE_EDITOR_HEAD_YAW_SLIDER, FACE_EDITOR_HEAD_ROLL_SLIDER ])
 
 
 def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider]:

facefusion/uis/components/face_enhancer_options.py

@@ -3,25 +3,28 @@ from typing import List, Optional, Tuple
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.common_helper import calc_int_step
+from facefusion.common_helper import calc_float_step, calc_int_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FaceEnhancerModel
+from facefusion.processors.types import FaceEnhancerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_ENHANCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_ENHANCER_BLEND_SLIDER : Optional[gradio.Slider] = None
+FACE_ENHANCER_WEIGHT_SLIDER : Optional[gradio.Slider] = None
 
 
 def render() -> None:
 	global FACE_ENHANCER_MODEL_DROPDOWN
 	global FACE_ENHANCER_BLEND_SLIDER
+	global FACE_ENHANCER_WEIGHT_SLIDER
 
+	has_face_enhancer = 'face_enhancer' in state_manager.get_item('processors')
 	FACE_ENHANCER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.face_enhancer_model_dropdown'),
 		choices = processors_choices.face_enhancer_models,
 		value = state_manager.get_item('face_enhancer_model'),
-		visible = 'face_enhancer' in state_manager.get_item('processors')
+		visible = has_face_enhancer
 	)
 	FACE_ENHANCER_BLEND_SLIDER = gradio.Slider(
 		label = wording.get('uis.face_enhancer_blend_slider'),
@@ -29,35 +32,50 @@ def render() -> None:
 		step = calc_int_step(processors_choices.face_enhancer_blend_range),
 		minimum = processors_choices.face_enhancer_blend_range[0],
 		maximum = processors_choices.face_enhancer_blend_range[-1],
-		visible = 'face_enhancer' in state_manager.get_item('processors')
+		visible = has_face_enhancer
+	)
+	FACE_ENHANCER_WEIGHT_SLIDER = gradio.Slider(
+		label = wording.get('uis.face_enhancer_weight_slider'),
+		value = state_manager.get_item('face_enhancer_weight'),
+		step = calc_float_step(processors_choices.face_enhancer_weight_range),
+		minimum = processors_choices.face_enhancer_weight_range[0],
+		maximum = processors_choices.face_enhancer_weight_range[-1],
+		visible = has_face_enhancer and load_processor_module('face_enhancer').get_inference_pool() and load_processor_module('face_enhancer').has_weight_input()
 	)
 	register_ui_component('face_enhancer_model_dropdown', FACE_ENHANCER_MODEL_DROPDOWN)
 	register_ui_component('face_enhancer_blend_slider', FACE_ENHANCER_BLEND_SLIDER)
+	register_ui_component('face_enhancer_weight_slider', FACE_ENHANCER_WEIGHT_SLIDER)
 
 
 def listen() -> None:
-	FACE_ENHANCER_MODEL_DROPDOWN.change(update_face_enhancer_model, inputs = FACE_ENHANCER_MODEL_DROPDOWN, outputs = FACE_ENHANCER_MODEL_DROPDOWN)
+	FACE_ENHANCER_MODEL_DROPDOWN.change(update_face_enhancer_model, inputs = FACE_ENHANCER_MODEL_DROPDOWN, outputs = [ FACE_ENHANCER_MODEL_DROPDOWN, FACE_ENHANCER_WEIGHT_SLIDER ])
 	FACE_ENHANCER_BLEND_SLIDER.release(update_face_enhancer_blend, inputs = FACE_ENHANCER_BLEND_SLIDER)
+	FACE_ENHANCER_WEIGHT_SLIDER.release(update_face_enhancer_weight, inputs = FACE_ENHANCER_WEIGHT_SLIDER)
 
 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ FACE_ENHANCER_MODEL_DROPDOWN, FACE_ENHANCER_BLEND_SLIDER ])
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ FACE_ENHANCER_MODEL_DROPDOWN, FACE_ENHANCER_BLEND_SLIDER, FACE_ENHANCER_WEIGHT_SLIDER ])
 
 
-def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider]:
+def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider, gradio.Slider]:
 	has_face_enhancer = 'face_enhancer' in processors
-	return gradio.Dropdown(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer)
+	return gradio.Dropdown(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer), gradio.Slider(visible = has_face_enhancer and load_processor_module('face_enhancer').get_inference_pool() and load_processor_module('face_enhancer').has_weight_input())
 
 
-def update_face_enhancer_model(face_enhancer_model : FaceEnhancerModel) -> gradio.Dropdown:
+def update_face_enhancer_model(face_enhancer_model : FaceEnhancerModel) -> Tuple[gradio.Dropdown, gradio.Slider]:
 	face_enhancer_module = load_processor_module('face_enhancer')
 	face_enhancer_module.clear_inference_pool()
 	state_manager.set_item('face_enhancer_model', face_enhancer_model)
 
 	if face_enhancer_module.pre_check():
-		return gradio.Dropdown(value = state_manager.get_item('face_enhancer_model'))
-	return gradio.Dropdown()
+		return gradio.Dropdown(value = state_manager.get_item('face_enhancer_model')), gradio.Slider(visible = face_enhancer_module.has_weight_input())
+	return gradio.Dropdown(), gradio.Slider()
 
 
 def update_face_enhancer_blend(face_enhancer_blend : float) -> None:
 	state_manager.set_item('face_enhancer_blend', int(face_enhancer_blend))
+
+
+def update_face_enhancer_weight(face_enhancer_weight : float) -> None:
+	state_manager.set_item('face_enhancer_weight', face_enhancer_weight)
+

facefusion/uis/components/face_landmarker.py

@@ -5,7 +5,7 @@ import gradio
 import facefusion.choices
 from facefusion import face_landmarker, state_manager, wording
 from facefusion.common_helper import calc_float_step
-from facefusion.typing import FaceLandmarkerModel, Score
+from facefusion.types import FaceLandmarkerModel, Score
 from facefusion.uis.core import register_ui_component
 
 FACE_LANDMARKER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None

facefusion/uis/components/face_masker.py

@@ -3,12 +3,15 @@ from typing import List, Optional, Tuple
 import gradio
 
 import facefusion.choices
-from facefusion import state_manager, wording
+from facefusion import face_masker, state_manager, wording
 from facefusion.common_helper import calc_float_step, calc_int_step
-from facefusion.typing import FaceMaskRegion, FaceMaskType
+from facefusion.types import FaceMaskArea, FaceMaskRegion, FaceMaskType, FaceOccluderModel, FaceParserModel
 from facefusion.uis.core import register_ui_component
 
+FACE_OCCLUDER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
+FACE_PARSER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_MASK_TYPES_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
+FACE_MASK_AREAS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 FACE_MASK_REGIONS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
 FACE_MASK_BLUR_SLIDER : Optional[gradio.Slider] = None
 FACE_MASK_PADDING_TOP_SLIDER : Optional[gradio.Slider] = None
@@ -18,7 +21,10 @@ FACE_MASK_PADDING_LEFT_SLIDER : Optional[gradio.Slider] = None
 
 
 def render() -> None:
+	global FACE_OCCLUDER_MODEL_DROPDOWN
+	global FACE_PARSER_MODEL_DROPDOWN
 	global FACE_MASK_TYPES_CHECKBOX_GROUP
+	global FACE_MASK_AREAS_CHECKBOX_GROUP
 	global FACE_MASK_REGIONS_CHECKBOX_GROUP
 	global FACE_MASK_BLUR_SLIDER
 	global FACE_MASK_PADDING_TOP_SLIDER
@@ -28,11 +34,29 @@ def render() -> None:
 
 	has_box_mask = 'box' in state_manager.get_item('face_mask_types')
 	has_region_mask = 'region' in state_manager.get_item('face_mask_types')
+	has_area_mask = 'area' in state_manager.get_item('face_mask_types')
+	with gradio.Row():
+		FACE_OCCLUDER_MODEL_DROPDOWN = gradio.Dropdown(
+			label = wording.get('uis.face_occluder_model_dropdown'),
+			choices = facefusion.choices.face_occluder_models,
+			value = state_manager.get_item('face_occluder_model')
+		)
+		FACE_PARSER_MODEL_DROPDOWN = gradio.Dropdown(
+			label = wording.get('uis.face_parser_model_dropdown'),
+			choices = facefusion.choices.face_parser_models,
+			value = state_manager.get_item('face_parser_model')
+		)
 	FACE_MASK_TYPES_CHECKBOX_GROUP = gradio.CheckboxGroup(
 		label = wording.get('uis.face_mask_types_checkbox_group'),
 		choices = facefusion.choices.face_mask_types,
 		value = state_manager.get_item('face_mask_types')
 	)
+	FACE_MASK_AREAS_CHECKBOX_GROUP = gradio.CheckboxGroup(
+		label = wording.get('uis.face_mask_areas_checkbox_group'),
+		choices = facefusion.choices.face_mask_areas,
+		value = state_manager.get_item('face_mask_areas'),
+		visible = has_area_mask
+	)
 	FACE_MASK_REGIONS_CHECKBOX_GROUP = gradio.CheckboxGroup(
 		label = wording.get('uis.face_mask_regions_checkbox_group'),
 		choices = facefusion.choices.face_mask_regions,
@@ -82,7 +106,10 @@ def render() -> None:
 				value = state_manager.get_item('face_mask_padding')[3],
 				visible = has_box_mask
 			)
+	register_ui_component('face_occluder_model_dropdown', FACE_OCCLUDER_MODEL_DROPDOWN)
+	register_ui_component('face_parser_model_dropdown', FACE_PARSER_MODEL_DROPDOWN)
 	register_ui_component('face_mask_types_checkbox_group', FACE_MASK_TYPES_CHECKBOX_GROUP)
+	register_ui_component('face_mask_areas_checkbox_group', FACE_MASK_AREAS_CHECKBOX_GROUP)
 	register_ui_component('face_mask_regions_checkbox_group', FACE_MASK_REGIONS_CHECKBOX_GROUP)
 	register_ui_component('face_mask_blur_slider', FACE_MASK_BLUR_SLIDER)
 	register_ui_component('face_mask_padding_top_slider', FACE_MASK_PADDING_TOP_SLIDER)
@@ -92,20 +119,49 @@ def render() -> None:
 
 
 def listen() -> None:
-	FACE_MASK_TYPES_CHECKBOX_GROUP.change(update_face_mask_types, inputs = FACE_MASK_TYPES_CHECKBOX_GROUP, outputs = [ FACE_MASK_TYPES_CHECKBOX_GROUP, FACE_MASK_REGIONS_CHECKBOX_GROUP, FACE_MASK_BLUR_SLIDER, FACE_MASK_PADDING_TOP_SLIDER, FACE_MASK_PADDING_RIGHT_SLIDER, FACE_MASK_PADDING_BOTTOM_SLIDER, FACE_MASK_PADDING_LEFT_SLIDER ])
+	FACE_OCCLUDER_MODEL_DROPDOWN.change(update_face_occluder_model, inputs = FACE_OCCLUDER_MODEL_DROPDOWN)
+	FACE_PARSER_MODEL_DROPDOWN.change(update_face_parser_model, inputs = FACE_PARSER_MODEL_DROPDOWN)
+	FACE_MASK_TYPES_CHECKBOX_GROUP.change(update_face_mask_types, inputs = FACE_MASK_TYPES_CHECKBOX_GROUP, outputs = [ FACE_MASK_TYPES_CHECKBOX_GROUP, FACE_MASK_AREAS_CHECKBOX_GROUP, FACE_MASK_REGIONS_CHECKBOX_GROUP, FACE_MASK_BLUR_SLIDER, FACE_MASK_PADDING_TOP_SLIDER, FACE_MASK_PADDING_RIGHT_SLIDER, FACE_MASK_PADDING_BOTTOM_SLIDER, FACE_MASK_PADDING_LEFT_SLIDER ])
+	FACE_MASK_AREAS_CHECKBOX_GROUP.change(update_face_mask_areas, inputs = FACE_MASK_AREAS_CHECKBOX_GROUP, outputs = FACE_MASK_AREAS_CHECKBOX_GROUP)
 	FACE_MASK_REGIONS_CHECKBOX_GROUP.change(update_face_mask_regions, inputs = FACE_MASK_REGIONS_CHECKBOX_GROUP, outputs = FACE_MASK_REGIONS_CHECKBOX_GROUP)
 	FACE_MASK_BLUR_SLIDER.release(update_face_mask_blur, inputs = FACE_MASK_BLUR_SLIDER)
+
 	face_mask_padding_sliders = [ FACE_MASK_PADDING_TOP_SLIDER, FACE_MASK_PADDING_RIGHT_SLIDER, FACE_MASK_PADDING_BOTTOM_SLIDER, FACE_MASK_PADDING_LEFT_SLIDER ]
 	for face_mask_padding_slider in face_mask_padding_sliders:
 		face_mask_padding_slider.release(update_face_mask_padding, inputs = face_mask_padding_sliders)
 
 
-def update_face_mask_types(face_mask_types : List[FaceMaskType]) -> Tuple[gradio.CheckboxGroup, gradio.CheckboxGroup, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider]:
+def update_face_occluder_model(face_occluder_model : FaceOccluderModel) -> gradio.Dropdown:
+	face_masker.clear_inference_pool()
+	state_manager.set_item('face_occluder_model', face_occluder_model)
+
+	if face_masker.pre_check():
+		return gradio.Dropdown(value = state_manager.get_item('face_occluder_model'))
+	return gradio.Dropdown()
+
+
+def update_face_parser_model(face_parser_model : FaceParserModel) -> gradio.Dropdown:
+	face_masker.clear_inference_pool()
+	state_manager.set_item('face_parser_model', face_parser_model)
+
+	if face_masker.pre_check():
+		return gradio.Dropdown(value = state_manager.get_item('face_parser_model'))
+	return gradio.Dropdown()
+
+
+def update_face_mask_types(face_mask_types : List[FaceMaskType]) -> Tuple[gradio.CheckboxGroup, gradio.CheckboxGroup, gradio.CheckboxGroup, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider, gradio.Slider]:
 	face_mask_types = face_mask_types or facefusion.choices.face_mask_types
 	state_manager.set_item('face_mask_types', face_mask_types)
 	has_box_mask = 'box' in face_mask_types
+	has_area_mask = 'area' in face_mask_types
 	has_region_mask = 'region' in face_mask_types
-	return gradio.CheckboxGroup(value = state_manager.get_item('face_mask_types')), gradio.CheckboxGroup(visible = has_region_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask)
+	return gradio.CheckboxGroup(value = state_manager.get_item('face_mask_types')), gradio.CheckboxGroup(visible = has_area_mask), gradio.CheckboxGroup(visible = has_region_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask), gradio.Slider(visible = has_box_mask)
+
+
+def update_face_mask_areas(face_mask_areas : List[FaceMaskArea]) -> gradio.CheckboxGroup:
+	face_mask_areas = face_mask_areas or facefusion.choices.face_mask_areas
+	state_manager.set_item('face_mask_areas', face_mask_areas)
+	return gradio.CheckboxGroup(value = state_manager.get_item('face_mask_areas'))
 
 
 def update_face_mask_regions(face_mask_regions : List[FaceMaskRegion]) -> gradio.CheckboxGroup:

facefusion/uis/components/face_selector.py

@@ -10,11 +10,11 @@ from facefusion.face_analyser import get_many_faces
 from facefusion.face_selector import sort_and_filter_faces
 from facefusion.face_store import clear_reference_faces, clear_static_faces
 from facefusion.filesystem import is_image, is_video
-from facefusion.typing import FaceSelectorMode, FaceSelectorOrder, Gender, Race, VisionFrame
+from facefusion.types import FaceSelectorMode, FaceSelectorOrder, Gender, Race, VisionFrame
 from facefusion.uis.core import get_ui_component, get_ui_components, register_ui_component
-from facefusion.uis.typing import ComponentOptions
+from facefusion.uis.types import ComponentOptions
 from facefusion.uis.ui_helper import convert_str_none
-from facefusion.vision import get_video_frame, normalize_frame_color, read_static_image
+from facefusion.vision import normalize_frame_color, read_static_image, read_video_frame
 
 FACE_SELECTOR_MODE_DROPDOWN : Optional[gradio.Dropdown] = None
 FACE_SELECTOR_ORDER_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -38,15 +38,16 @@ def render() -> None:
 	{
 		'label': wording.get('uis.reference_face_gallery'),
 		'object_fit': 'cover',
-		'columns': 8,
+		'columns': 7,
 		'allow_preview': False,
+		'elem_classes': 'box-face-selector',
 		'visible': 'reference' in state_manager.get_item('face_selector_mode')
 	}
 	if is_image(state_manager.get_item('target_path')):
 		reference_frame = read_static_image(state_manager.get_item('target_path'))
 		reference_face_gallery_options['value'] = extract_gallery_frames(reference_frame)
 	if is_video(state_manager.get_item('target_path')):
-		reference_frame = get_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
+		reference_frame = read_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
 		reference_face_gallery_options['value'] = extract_gallery_frames(reference_frame)
 	FACE_SELECTOR_MODE_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.face_selector_mode_dropdown'),
@@ -112,7 +113,7 @@ def listen() -> None:
 		'target_image',
 		'target_video'
 	]):
-		for method in [ 'upload', 'change', 'clear' ]:
+		for method in [ 'change', 'clear' ]:
 			getattr(ui_component, method)(update_reference_face_position)
 			getattr(ui_component, method)(update_reference_position_gallery, outputs = REFERENCE_FACE_POSITION_GALLERY)
 
@@ -130,8 +131,9 @@ def listen() -> None:
 
 	preview_frame_slider = get_ui_component('preview_frame_slider')
 	if preview_frame_slider:
-		preview_frame_slider.release(update_reference_frame_number, inputs = preview_frame_slider)
-		preview_frame_slider.release(update_reference_position_gallery, outputs = REFERENCE_FACE_POSITION_GALLERY)
+		for method in [ 'change', 'release' ]:
+			getattr(preview_frame_slider, method)(update_reference_frame_number, inputs = preview_frame_slider, show_progress = 'hidden')
+			getattr(preview_frame_slider, method)(update_reference_position_gallery, outputs = REFERENCE_FACE_POSITION_GALLERY, show_progress = 'hidden')
 
 
 def update_face_selector_mode(face_selector_mode : FaceSelectorMode) -> Tuple[gradio.Gallery, gradio.Slider]:
@@ -197,7 +199,7 @@ def update_reference_position_gallery() -> gradio.Gallery:
 		temp_vision_frame = read_static_image(state_manager.get_item('target_path'))
 		gallery_vision_frames = extract_gallery_frames(temp_vision_frame)
 	if is_video(state_manager.get_item('target_path')):
-		temp_vision_frame = get_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
+		temp_vision_frame = read_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
 		gallery_vision_frames = extract_gallery_frames(temp_vision_frame)
 	if gallery_vision_frames:
 		return gradio.Gallery(value = gallery_vision_frames)

facefusion/uis/components/face_swapper_options.py

@@ -6,7 +6,7 @@ from facefusion import state_manager, wording
 from facefusion.common_helper import get_first
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FaceSwapperModel
+from facefusion.processors.types import FaceSwapperModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FACE_SWAPPER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -17,17 +17,18 @@ def render() -> None:
 	global FACE_SWAPPER_MODEL_DROPDOWN
 	global FACE_SWAPPER_PIXEL_BOOST_DROPDOWN
 
+	has_face_swapper = 'face_swapper' in state_manager.get_item('processors')
 	FACE_SWAPPER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.face_swapper_model_dropdown'),
-		choices = processors_choices.face_swapper_set.keys(),
+		choices = processors_choices.face_swapper_models,
 		value = state_manager.get_item('face_swapper_model'),
-		visible = 'face_swapper' in state_manager.get_item('processors')
+		visible = has_face_swapper
 	)
 	FACE_SWAPPER_PIXEL_BOOST_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.face_swapper_pixel_boost_dropdown'),
 		choices = processors_choices.face_swapper_set.get(state_manager.get_item('face_swapper_model')),
 		value = state_manager.get_item('face_swapper_pixel_boost'),
-		visible = 'face_swapper' in state_manager.get_item('processors')
+		visible = has_face_swapper
 	)
 	register_ui_component('face_swapper_model_dropdown', FACE_SWAPPER_MODEL_DROPDOWN)
 	register_ui_component('face_swapper_pixel_boost_dropdown', FACE_SWAPPER_PIXEL_BOOST_DROPDOWN)

facefusion/uis/components/frame_colorizer_options.py

@@ -6,7 +6,7 @@ from facefusion import state_manager, wording
 from facefusion.common_helper import calc_int_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FrameColorizerModel
+from facefusion.processors.types import FrameColorizerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FRAME_COLORIZER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -19,17 +19,18 @@ def render() -> None:
 	global FRAME_COLORIZER_SIZE_DROPDOWN
 	global FRAME_COLORIZER_BLEND_SLIDER
 
+	has_frame_colorizer = 'frame_colorizer' in state_manager.get_item('processors')
 	FRAME_COLORIZER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.frame_colorizer_model_dropdown'),
 		choices = processors_choices.frame_colorizer_models,
 		value = state_manager.get_item('frame_colorizer_model'),
-		visible = 'frame_colorizer' in state_manager.get_item('processors')
+		visible = has_frame_colorizer
 	)
 	FRAME_COLORIZER_SIZE_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.frame_colorizer_size_dropdown'),
 		choices = processors_choices.frame_colorizer_sizes,
 		value = state_manager.get_item('frame_colorizer_size'),
-		visible = 'frame_colorizer' in state_manager.get_item('processors')
+		visible = has_frame_colorizer
 	)
 	FRAME_COLORIZER_BLEND_SLIDER = gradio.Slider(
 		label = wording.get('uis.frame_colorizer_blend_slider'),
@@ -37,7 +38,7 @@ def render() -> None:
 		step = calc_int_step(processors_choices.frame_colorizer_blend_range),
 		minimum = processors_choices.frame_colorizer_blend_range[0],
 		maximum = processors_choices.frame_colorizer_blend_range[-1],
-		visible = 'frame_colorizer' in state_manager.get_item('processors')
+		visible = has_frame_colorizer
 	)
 	register_ui_component('frame_colorizer_model_dropdown', FRAME_COLORIZER_MODEL_DROPDOWN)
 	register_ui_component('frame_colorizer_size_dropdown', FRAME_COLORIZER_SIZE_DROPDOWN)

facefusion/uis/components/frame_enhancer_options.py

@@ -6,7 +6,7 @@ from facefusion import state_manager, wording
 from facefusion.common_helper import calc_int_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import FrameEnhancerModel
+from facefusion.processors.types import FrameEnhancerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 FRAME_ENHANCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -17,11 +17,12 @@ def render() -> None:
 	global FRAME_ENHANCER_MODEL_DROPDOWN
 	global FRAME_ENHANCER_BLEND_SLIDER
 
+	has_frame_enhancer = 'frame_enhancer' in state_manager.get_item('processors')
 	FRAME_ENHANCER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.frame_enhancer_model_dropdown'),
 		choices = processors_choices.frame_enhancer_models,
 		value = state_manager.get_item('frame_enhancer_model'),
-		visible = 'frame_enhancer' in state_manager.get_item('processors')
+		visible = has_frame_enhancer
 	)
 	FRAME_ENHANCER_BLEND_SLIDER = gradio.Slider(
 		label = wording.get('uis.frame_enhancer_blend_slider'),
@@ -29,7 +30,7 @@ def render() -> None:
 		step = calc_int_step(processors_choices.frame_enhancer_blend_range),
 		minimum = processors_choices.frame_enhancer_blend_range[0],
 		maximum = processors_choices.frame_enhancer_blend_range[-1],
-		visible = 'frame_enhancer' in state_manager.get_item('processors')
+		visible = has_frame_enhancer
 	)
 	register_ui_component('frame_enhancer_model_dropdown', FRAME_ENHANCER_MODEL_DROPDOWN)
 	register_ui_component('frame_enhancer_blend_slider', FRAME_ENHANCER_BLEND_SLIDER)

facefusion/uis/components/instant_runner.py

@@ -9,7 +9,7 @@ from facefusion.core import process_step
 from facefusion.filesystem import is_directory, is_image, is_video
 from facefusion.jobs import job_helper, job_manager, job_runner, job_store
 from facefusion.temp_helper import clear_temp_directory
-from facefusion.typing import Args, UiWorkflow
+from facefusion.types import Args, UiWorkflow
 from facefusion.uis.core import get_ui_component
 from facefusion.uis.ui_helper import suggest_output_path
 
@@ -92,7 +92,7 @@ def create_and_run_job(step_args : Args) -> bool:
 	job_id = job_helper.suggest_job_id('ui')
 
 	for key in job_store.get_job_keys():
-		state_manager.sync_item(key) #type:ignore
+		state_manager.sync_item(key) #type:ignore[arg-type]
 
 	return job_manager.create_job(job_id) and job_manager.add_step(job_id, step_args) and job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step)
 

facefusion/uis/components/job_list.py

@@ -6,7 +6,7 @@ import facefusion.choices
 from facefusion import state_manager, wording
 from facefusion.common_helper import get_first
 from facefusion.jobs import job_list, job_manager
-from facefusion.typing import JobStatus
+from facefusion.types import JobStatus
 from facefusion.uis.core import get_ui_component
 
 JOB_LIST_JOBS_DATAFRAME : Optional[gradio.Dataframe] = None

facefusion/uis/components/job_list_options.py

@@ -6,7 +6,7 @@ import facefusion.choices
 from facefusion import state_manager, wording
 from facefusion.common_helper import get_first
 from facefusion.jobs import job_manager
-from facefusion.typing import JobStatus
+from facefusion.types import JobStatus
 from facefusion.uis.core import register_ui_component
 
 JOB_LIST_JOB_STATUS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None

facefusion/uis/components/job_manager.py

@@ -7,10 +7,10 @@ from facefusion.args import collect_step_args
 from facefusion.common_helper import get_first, get_last
 from facefusion.filesystem import is_directory
 from facefusion.jobs import job_manager
-from facefusion.typing import UiWorkflow
+from facefusion.types import UiWorkflow
 from facefusion.uis import choices as uis_choices
 from facefusion.uis.core import get_ui_component
-from facefusion.uis.typing import JobManagerAction
+from facefusion.uis.types import JobManagerAction
 from facefusion.uis.ui_helper import convert_int_none, convert_str_none, suggest_output_path
 
 JOB_MANAGER_WRAPPER : Optional[gradio.Column] = None
@@ -89,6 +89,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 
 	if is_directory(step_args.get('output_path')):
 		step_args['output_path'] = suggest_output_path(step_args.get('output_path'), state_manager.get_item('target_path'))
+
 	if job_action == 'job-create':
 		if created_job_id and job_manager.create_job(created_job_id):
 			updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
@@ -97,6 +98,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 			return gradio.Dropdown(value = 'job-add-step'), gradio.Textbox(visible = False), gradio.Dropdown(value = created_job_id, choices = updated_job_ids, visible = True), gradio.Dropdown()
 		else:
 			logger.error(wording.get('job_not_created').format(job_id = created_job_id), __name__)
+
 	if job_action == 'job-submit':
 		if selected_job_id and job_manager.submit_job(selected_job_id):
 			updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
@@ -105,6 +107,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 			return gradio.Dropdown(), gradio.Textbox(), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids, visible = True), gradio.Dropdown()
 		else:
 			logger.error(wording.get('job_not_submitted').format(job_id = selected_job_id), __name__)
+
 	if job_action == 'job-delete':
 		if selected_job_id and job_manager.delete_job(selected_job_id):
 			updated_job_ids = job_manager.find_job_ids('drafted') + job_manager.find_job_ids('queued') + job_manager.find_job_ids('failed') + job_manager.find_job_ids('completed') or [ 'none' ]
@@ -113,6 +116,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 			return gradio.Dropdown(), gradio.Textbox(), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids, visible = True), gradio.Dropdown()
 		else:
 			logger.error(wording.get('job_not_deleted').format(job_id = selected_job_id), __name__)
+
 	if job_action == 'job-add-step':
 		if selected_job_id and job_manager.add_step(selected_job_id, step_args):
 			state_manager.set_item('output_path', output_path)
@@ -121,6 +125,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 		else:
 			state_manager.set_item('output_path', output_path)
 			logger.error(wording.get('job_step_not_added').format(job_id = selected_job_id), __name__)
+
 	if job_action == 'job-remix-step':
 		if selected_job_id and job_manager.has_step(selected_job_id, selected_step_index) and job_manager.remix_step(selected_job_id, selected_step_index, step_args):
 			updated_step_choices = get_step_choices(selected_job_id) or [ 'none' ] #type:ignore[list-item]
@@ -131,6 +136,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 		else:
 			state_manager.set_item('output_path', output_path)
 			logger.error(wording.get('job_remix_step_not_added').format(job_id = selected_job_id, step_index = selected_step_index), __name__)
+
 	if job_action == 'job-insert-step':
 		if selected_job_id and job_manager.has_step(selected_job_id, selected_step_index) and job_manager.insert_step(selected_job_id, selected_step_index, step_args):
 			updated_step_choices = get_step_choices(selected_job_id) or [ 'none' ] #type:ignore[list-item]
@@ -141,6 +147,7 @@ def apply(job_action : JobManagerAction, created_job_id : str, selected_job_id :
 		else:
 			state_manager.set_item('output_path', output_path)
 			logger.error(wording.get('job_step_not_inserted').format(job_id = selected_job_id, step_index = selected_step_index), __name__)
+
 	if job_action == 'job-remove-step':
 		if selected_job_id and job_manager.has_step(selected_job_id, selected_step_index) and job_manager.remove_step(selected_job_id, selected_step_index):
 			updated_step_choices = get_step_choices(selected_job_id) or [ 'none' ] #type:ignore[list-item]
@@ -160,16 +167,19 @@ def get_step_choices(job_id : str) -> List[int]:
 def update(job_action : JobManagerAction, selected_job_id : str) -> Tuple[gradio.Textbox, gradio.Dropdown, gradio.Dropdown]:
 	if job_action == 'job-create':
 		return gradio.Textbox(value = None, visible = True), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False)
+
 	if job_action == 'job-delete':
 		updated_job_ids = job_manager.find_job_ids('drafted') + job_manager.find_job_ids('queued') + job_manager.find_job_ids('failed') + job_manager.find_job_ids('completed') or [ 'none' ]
 		updated_job_id = selected_job_id if selected_job_id in updated_job_ids else get_last(updated_job_ids)
 
 		return gradio.Textbox(visible = False), gradio.Dropdown(value = updated_job_id, choices = updated_job_ids, visible = True), gradio.Dropdown(visible = False)
+
 	if job_action in [ 'job-submit', 'job-add-step' ]:
 		updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
 		updated_job_id = selected_job_id if selected_job_id in updated_job_ids else get_last(updated_job_ids)
 
 		return gradio.Textbox(visible = False), gradio.Dropdown(value = updated_job_id, choices = updated_job_ids, visible = True), gradio.Dropdown(visible = False)
+
 	if job_action in [ 'job-remix-step', 'job-insert-step', 'job-remove-step' ]:
 		updated_job_ids = job_manager.find_job_ids('drafted') or [ 'none' ]
 		updated_job_id = selected_job_id if selected_job_id in updated_job_ids else get_last(updated_job_ids)

facefusion/uis/components/job_runner.py

@@ -7,10 +7,10 @@ from facefusion import logger, process_manager, state_manager, wording
 from facefusion.common_helper import get_first, get_last
 from facefusion.core import process_step
 from facefusion.jobs import job_manager, job_runner, job_store
-from facefusion.typing import UiWorkflow
+from facefusion.types import UiWorkflow
 from facefusion.uis import choices as uis_choices
 from facefusion.uis.core import get_ui_component
-from facefusion.uis.typing import JobRunnerAction
+from facefusion.uis.types import JobRunnerAction
 from facefusion.uis.ui_helper import convert_str_none
 
 JOB_RUNNER_WRAPPER : Optional[gradio.Column] = None
@@ -84,7 +84,7 @@ def run(job_action : JobRunnerAction, job_id : str) -> Tuple[gradio.Button, grad
 	job_id = convert_str_none(job_id)
 
 	for key in job_store.get_job_keys():
-		state_manager.sync_item(key) #type:ignore
+		state_manager.sync_item(key) #type:ignore[arg-type]
 
 	if job_action == 'job-run':
 		logger.info(wording.get('running_job').format(job_id = job_id), __name__)
@@ -95,12 +95,15 @@ def run(job_action : JobRunnerAction, job_id : str) -> Tuple[gradio.Button, grad
 		updated_job_ids = job_manager.find_job_ids('queued') or [ 'none' ]
 
 		return gradio.Button(visible = True), gradio.Button(visible = False), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids)
+
 	if job_action == 'job-run-all':
 		logger.info(wording.get('running_jobs'), __name__)
-		if job_runner.run_jobs(process_step):
+		halt_on_error = False
+		if job_runner.run_jobs(process_step, halt_on_error):
 			logger.info(wording.get('processing_jobs_succeed'), __name__)
 		else:
 			logger.info(wording.get('processing_jobs_failed'), __name__)
+
 	if job_action == 'job-retry':
 		logger.info(wording.get('retrying_job').format(job_id = job_id), __name__)
 		if job_id and job_runner.retry_job(job_id, process_step):
@@ -110,9 +113,11 @@ def run(job_action : JobRunnerAction, job_id : str) -> Tuple[gradio.Button, grad
 		updated_job_ids = job_manager.find_job_ids('failed') or [ 'none' ]
 
 		return gradio.Button(visible = True), gradio.Button(visible = False), gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids)
+
 	if job_action == 'job-retry-all':
 		logger.info(wording.get('retrying_jobs'), __name__)
-		if job_runner.retry_jobs(process_step):
+		halt_on_error = False
+		if job_runner.retry_jobs(process_step, halt_on_error):
 			logger.info(wording.get('processing_jobs_succeed'), __name__)
 		else:
 			logger.info(wording.get('processing_jobs_failed'), __name__)
@@ -129,6 +134,7 @@ def update_job_action(job_action : JobRunnerAction) -> gradio.Dropdown:
 		updated_job_ids = job_manager.find_job_ids('queued') or [ 'none' ]
 
 		return gradio.Dropdown(value = get_last(updated_job_ids), choices = updated_job_ids, visible = True)
+
 	if job_action == 'job-retry':
 		updated_job_ids = job_manager.find_job_ids('failed') or [ 'none' ]
 

facefusion/uis/components/lip_syncer_options.py

@@ -1,39 +1,53 @@
-from typing import List, Optional
+from typing import List, Optional, Tuple
 
 import gradio
 
 from facefusion import state_manager, wording
+from facefusion.common_helper import calc_float_step
 from facefusion.processors import choices as processors_choices
 from facefusion.processors.core import load_processor_module
-from facefusion.processors.typing import LipSyncerModel
+from facefusion.processors.types import LipSyncerModel
 from facefusion.uis.core import get_ui_component, register_ui_component
 
 LIP_SYNCER_MODEL_DROPDOWN : Optional[gradio.Dropdown] = None
+LIP_SYNCER_WEIGHT_SLIDER : Optional[gradio.Slider] = None
 
 
 def render() -> None:
 	global LIP_SYNCER_MODEL_DROPDOWN
+	global LIP_SYNCER_WEIGHT_SLIDER
 
+	has_lip_syncer = 'lip_syncer' in state_manager.get_item('processors')
 	LIP_SYNCER_MODEL_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.lip_syncer_model_dropdown'),
 		choices = processors_choices.lip_syncer_models,
 		value = state_manager.get_item('lip_syncer_model'),
-		visible = 'lip_syncer' in state_manager.get_item('processors')
+		visible = has_lip_syncer
+	)
+	LIP_SYNCER_WEIGHT_SLIDER = gradio.Slider(
+		label = wording.get('uis.lip_syncer_weight_slider'),
+		value = state_manager.get_item('lip_syncer_weight'),
+		step = calc_float_step(processors_choices.lip_syncer_weight_range),
+		minimum = processors_choices.lip_syncer_weight_range[0],
+		maximum = processors_choices.lip_syncer_weight_range[-1],
+		visible = has_lip_syncer
 	)
 	register_ui_component('lip_syncer_model_dropdown', LIP_SYNCER_MODEL_DROPDOWN)
+	register_ui_component('lip_syncer_weight_slider', LIP_SYNCER_WEIGHT_SLIDER)
 
 
 def listen() -> None:
 	LIP_SYNCER_MODEL_DROPDOWN.change(update_lip_syncer_model, inputs = LIP_SYNCER_MODEL_DROPDOWN, outputs = LIP_SYNCER_MODEL_DROPDOWN)
+	LIP_SYNCER_WEIGHT_SLIDER.release(update_lip_syncer_weight, inputs = LIP_SYNCER_WEIGHT_SLIDER)
 
 	processors_checkbox_group = get_ui_component('processors_checkbox_group')
 	if processors_checkbox_group:
-		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = LIP_SYNCER_MODEL_DROPDOWN)
+		processors_checkbox_group.change(remote_update, inputs = processors_checkbox_group, outputs = [ LIP_SYNCER_MODEL_DROPDOWN, LIP_SYNCER_WEIGHT_SLIDER ])
 
 
-def remote_update(processors : List[str]) -> gradio.Dropdown:
+def remote_update(processors : List[str]) -> Tuple[gradio.Dropdown, gradio.Slider]:
 	has_lip_syncer = 'lip_syncer' in processors
-	return gradio.Dropdown(visible = has_lip_syncer)
+	return gradio.Dropdown(visible = has_lip_syncer), gradio.Slider(visible = has_lip_syncer)
 
 
 def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdown:
@@ -44,3 +58,7 @@ def update_lip_syncer_model(lip_syncer_model : LipSyncerModel) -> gradio.Dropdow
 	if lip_syncer_module.pre_check():
 		return gradio.Dropdown(value = state_manager.get_item('lip_syncer_model'))
 	return gradio.Dropdown()
+
+
+def update_lip_syncer_weight(lip_syncer_weight : float) -> None:
+	state_manager.set_item('lip_syncer_weight', lip_syncer_weight)

facefusion/uis/components/memory.py

@@ -5,7 +5,7 @@ import gradio
 import facefusion.choices
 from facefusion import state_manager, wording
 from facefusion.common_helper import calc_int_step
-from facefusion.typing import VideoMemoryStrategy
+from facefusion.types import VideoMemoryStrategy
 
 VIDEO_MEMORY_STRATEGY_DROPDOWN : Optional[gradio.Dropdown] = None
 SYSTEM_MEMORY_LIMIT_SLIDER : Optional[gradio.Slider] = None

facefusion/uis/components/output_options.py

@@ -5,14 +5,17 @@ import gradio
 import facefusion.choices
 from facefusion import state_manager, wording
 from facefusion.common_helper import calc_int_step
+from facefusion.ffmpeg import get_available_encoder_set
 from facefusion.filesystem import is_image, is_video
-from facefusion.typing import Fps, OutputAudioEncoder, OutputVideoEncoder, OutputVideoPreset
+from facefusion.types import AudioEncoder, Fps, VideoEncoder, VideoPreset
 from facefusion.uis.core import get_ui_components, register_ui_component
 from facefusion.vision import create_image_resolutions, create_video_resolutions, detect_image_resolution, detect_video_fps, detect_video_resolution, pack_resolution
 
 OUTPUT_IMAGE_QUALITY_SLIDER : Optional[gradio.Slider] = None
 OUTPUT_IMAGE_RESOLUTION_DROPDOWN : Optional[gradio.Dropdown] = None
 OUTPUT_AUDIO_ENCODER_DROPDOWN : Optional[gradio.Dropdown] = None
+OUTPUT_AUDIO_QUALITY_SLIDER : Optional[gradio.Slider] = None
+OUTPUT_AUDIO_VOLUME_SLIDER : Optional[gradio.Slider] = None
 OUTPUT_VIDEO_ENCODER_DROPDOWN : Optional[gradio.Dropdown] = None
 OUTPUT_VIDEO_PRESET_DROPDOWN : Optional[gradio.Dropdown] = None
 OUTPUT_VIDEO_RESOLUTION_DROPDOWN : Optional[gradio.Dropdown] = None
@@ -24,6 +27,8 @@ def render() -> None:
 	global OUTPUT_IMAGE_QUALITY_SLIDER
 	global OUTPUT_IMAGE_RESOLUTION_DROPDOWN
 	global OUTPUT_AUDIO_ENCODER_DROPDOWN
+	global OUTPUT_AUDIO_QUALITY_SLIDER
+	global OUTPUT_AUDIO_VOLUME_SLIDER
 	global OUTPUT_VIDEO_ENCODER_DROPDOWN
 	global OUTPUT_VIDEO_PRESET_DROPDOWN
 	global OUTPUT_VIDEO_RESOLUTION_DROPDOWN
@@ -32,6 +37,7 @@ def render() -> None:
 
 	output_image_resolutions = []
 	output_video_resolutions = []
+	available_encoder_set = get_available_encoder_set()
 	if is_image(state_manager.get_item('target_path')):
 		output_image_resolution = detect_image_resolution(state_manager.get_item('target_path'))
 		output_image_resolutions = create_image_resolutions(output_image_resolution)
@@ -54,13 +60,29 @@ def render() -> None:
 	)
 	OUTPUT_AUDIO_ENCODER_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.output_audio_encoder_dropdown'),
-		choices = facefusion.choices.output_audio_encoders,
+		choices = available_encoder_set.get('audio'),
 		value = state_manager.get_item('output_audio_encoder'),
 		visible = is_video(state_manager.get_item('target_path'))
 	)
+	OUTPUT_AUDIO_QUALITY_SLIDER = gradio.Slider(
+		label = wording.get('uis.output_audio_quality_slider'),
+		value = state_manager.get_item('output_audio_quality'),
+		step = calc_int_step(facefusion.choices.output_audio_quality_range),
+		minimum = facefusion.choices.output_audio_quality_range[0],
+		maximum = facefusion.choices.output_audio_quality_range[-1],
+		visible = is_video(state_manager.get_item('target_path'))
+	)
+	OUTPUT_AUDIO_VOLUME_SLIDER = gradio.Slider(
+		label = wording.get('uis.output_audio_volume_slider'),
+		value = state_manager.get_item('output_audio_volume'),
+		step = calc_int_step(facefusion.choices.output_audio_volume_range),
+		minimum = facefusion.choices.output_audio_volume_range[0],
+		maximum = facefusion.choices.output_audio_volume_range[-1],
+		visible = is_video(state_manager.get_item('target_path'))
+	)
 	OUTPUT_VIDEO_ENCODER_DROPDOWN = gradio.Dropdown(
 		label = wording.get('uis.output_video_encoder_dropdown'),
-		choices = facefusion.choices.output_video_encoders,
+		choices = available_encoder_set.get('video'),
 		value = state_manager.get_item('output_video_encoder'),
 		visible = is_video(state_manager.get_item('target_path'))
 	)
@@ -99,6 +121,8 @@ def listen() -> None:
 	OUTPUT_IMAGE_QUALITY_SLIDER.release(update_output_image_quality, inputs = OUTPUT_IMAGE_QUALITY_SLIDER)
 	OUTPUT_IMAGE_RESOLUTION_DROPDOWN.change(update_output_image_resolution, inputs = OUTPUT_IMAGE_RESOLUTION_DROPDOWN)
 	OUTPUT_AUDIO_ENCODER_DROPDOWN.change(update_output_audio_encoder, inputs = OUTPUT_AUDIO_ENCODER_DROPDOWN)
+	OUTPUT_AUDIO_QUALITY_SLIDER.release(update_output_audio_quality, inputs = OUTPUT_AUDIO_QUALITY_SLIDER)
+	OUTPUT_AUDIO_VOLUME_SLIDER.release(update_output_audio_volume, inputs = OUTPUT_AUDIO_VOLUME_SLIDER)
 	OUTPUT_VIDEO_ENCODER_DROPDOWN.change(update_output_video_encoder, inputs = OUTPUT_VIDEO_ENCODER_DROPDOWN)
 	OUTPUT_VIDEO_PRESET_DROPDOWN.change(update_output_video_preset, inputs = OUTPUT_VIDEO_PRESET_DROPDOWN)
 	OUTPUT_VIDEO_QUALITY_SLIDER.release(update_output_video_quality, inputs = OUTPUT_VIDEO_QUALITY_SLIDER)
@@ -110,23 +134,23 @@ def listen() -> None:
 		'target_image',
 		'target_video'
 	]):
-		for method in [ 'upload', 'change', 'clear' ]:
-			getattr(ui_component, method)(remote_update, outputs = [ OUTPUT_IMAGE_QUALITY_SLIDER, OUTPUT_IMAGE_RESOLUTION_DROPDOWN, OUTPUT_AUDIO_ENCODER_DROPDOWN, OUTPUT_VIDEO_ENCODER_DROPDOWN, OUTPUT_VIDEO_PRESET_DROPDOWN, OUTPUT_VIDEO_QUALITY_SLIDER, OUTPUT_VIDEO_RESOLUTION_DROPDOWN, OUTPUT_VIDEO_FPS_SLIDER ])
+		for method in [ 'change', 'clear' ]:
+			getattr(ui_component, method)(remote_update, outputs = [ OUTPUT_IMAGE_QUALITY_SLIDER, OUTPUT_IMAGE_RESOLUTION_DROPDOWN, OUTPUT_AUDIO_ENCODER_DROPDOWN, OUTPUT_AUDIO_QUALITY_SLIDER, OUTPUT_AUDIO_VOLUME_SLIDER, OUTPUT_VIDEO_ENCODER_DROPDOWN, OUTPUT_VIDEO_PRESET_DROPDOWN, OUTPUT_VIDEO_QUALITY_SLIDER, OUTPUT_VIDEO_RESOLUTION_DROPDOWN, OUTPUT_VIDEO_FPS_SLIDER ])
 
 
-def remote_update() -> Tuple[gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Dropdown, gradio.Slider]:
+def remote_update() -> Tuple[gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Slider, gradio.Dropdown, gradio.Dropdown, gradio.Slider, gradio.Dropdown, gradio.Slider]:
 	if is_image(state_manager.get_item('target_path')):
 		output_image_resolution = detect_image_resolution(state_manager.get_item('target_path'))
 		output_image_resolutions = create_image_resolutions(output_image_resolution)
 		state_manager.set_item('output_image_resolution', pack_resolution(output_image_resolution))
-		return gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_image_resolution'), choices = output_image_resolutions, visible = True), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
+		return gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_image_resolution'), choices = output_image_resolutions, visible = True), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
 	if is_video(state_manager.get_item('target_path')):
 		output_video_resolution = detect_video_resolution(state_manager.get_item('target_path'))
 		output_video_resolutions = create_video_resolutions(output_video_resolution)
 		state_manager.set_item('output_video_resolution', pack_resolution(output_video_resolution))
 		state_manager.set_item('output_video_fps', detect_video_fps(state_manager.get_item('target_path')))
-		return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = True), gradio.Dropdown(visible = True), gradio.Dropdown(visible = True), gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_video_resolution'), choices = output_video_resolutions, visible = True), gradio.Slider(value = state_manager.get_item('output_video_fps'), visible = True)
-	return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
+		return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = True), gradio.Slider(visible = True), gradio.Slider(visible = True), gradio.Dropdown(visible = True), gradio.Dropdown(visible = True), gradio.Slider(visible = True), gradio.Dropdown(value = state_manager.get_item('output_video_resolution'), choices = output_video_resolutions, visible = True), gradio.Slider(value = state_manager.get_item('output_video_fps'), visible = True)
+	return gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False), gradio.Dropdown(visible = False), gradio.Slider(visible = False)
 
 
 def update_output_image_quality(output_image_quality : float) -> None:
@@ -137,15 +161,23 @@ def update_output_image_resolution(output_image_resolution : str) -> None:
 	state_manager.set_item('output_image_resolution', output_image_resolution)
 
 
-def update_output_audio_encoder(output_audio_encoder : OutputAudioEncoder) -> None:
+def update_output_audio_encoder(output_audio_encoder : AudioEncoder) -> None:
 	state_manager.set_item('output_audio_encoder', output_audio_encoder)
 
 
-def update_output_video_encoder(output_video_encoder : OutputVideoEncoder) -> None:
+def update_output_audio_quality(output_audio_quality : float) -> None:
+	state_manager.set_item('output_audio_quality', int(output_audio_quality))
+
+
+def update_output_audio_volume(output_audio_volume: float) -> None:
+	state_manager.set_item('output_audio_volume', int(output_audio_volume))
+
+
+def update_output_video_encoder(output_video_encoder : VideoEncoder) -> None:
 	state_manager.set_item('output_video_encoder', output_video_encoder)
 
 
-def update_output_video_preset(output_video_preset : OutputVideoPreset) -> None:
+def update_output_video_preset(output_video_preset : VideoPreset) -> None:
 	state_manager.set_item('output_video_preset', output_video_preset)
 
 

facefusion/uis/components/preview.py

@@ -11,13 +11,14 @@ from facefusion.common_helper import get_first
 from facefusion.content_analyser import analyse_frame
 from facefusion.core import conditional_append_reference_faces
 from facefusion.face_analyser import get_average_face, get_many_faces
+from facefusion.face_selector import sort_faces_by_order
 from facefusion.face_store import clear_reference_faces, clear_static_faces, get_reference_faces
 from facefusion.filesystem import filter_audio_paths, is_image, is_video
 from facefusion.processors.core import get_processors_modules
-from facefusion.typing import AudioFrame, Face, FaceSet, VisionFrame
+from facefusion.types import AudioFrame, Face, FaceSet, VisionFrame
 from facefusion.uis.core import get_ui_component, get_ui_components, register_ui_component
-from facefusion.uis.typing import ComponentOptions
-from facefusion.vision import count_video_frame_total, detect_frame_orientation, get_video_frame, normalize_frame_color, read_static_image, read_static_images, resize_frame_resolution
+from facefusion.uis.types import ComponentOptions
+from facefusion.vision import count_video_frame_total, detect_frame_orientation, normalize_frame_color, read_static_image, read_static_images, read_video_frame, restrict_frame
 
 PREVIEW_IMAGE : Optional[gradio.Image] = None
 PREVIEW_FRAME_SLIDER : Optional[gradio.Slider] = None
@@ -59,7 +60,7 @@ def render() -> None:
 		preview_image_options['elem_classes'] = [ 'image-preview', 'is-' + detect_frame_orientation(preview_vision_frame) ]
 
 	if is_video(state_manager.get_item('target_path')):
-		temp_vision_frame = get_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
+		temp_vision_frame = read_video_frame(state_manager.get_item('target_path'), state_manager.get_item('reference_frame_number'))
 		preview_vision_frame = process_preview_frame(reference_faces, source_face, source_audio_frame, temp_vision_frame)
 		preview_image_options['value'] = normalize_frame_color(preview_vision_frame)
 		preview_image_options['elem_classes'] = [ 'image-preview', 'is-' + detect_frame_orientation(preview_vision_frame) ]
@@ -74,7 +75,7 @@ def render() -> None:
 
 def listen() -> None:
 	PREVIEW_FRAME_SLIDER.release(update_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE, show_progress = 'hidden')
-	PREVIEW_FRAME_SLIDER.change(slide_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE, show_progress = 'hidden')
+	PREVIEW_FRAME_SLIDER.change(slide_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE, show_progress = 'hidden', trigger_mode = 'once')
 
 	reference_face_position_gallery = get_ui_component('reference_face_position_gallery')
 	if reference_face_position_gallery:
@@ -87,7 +88,7 @@ def listen() -> None:
 		'target_image',
 		'target_video'
 	]):
-		for method in [ 'upload', 'change', 'clear' ]:
+		for method in [ 'change', 'clear' ]:
 			getattr(ui_component, method)(update_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE)
 
 	for ui_component in get_ui_components(
@@ -95,7 +96,7 @@ def listen() -> None:
 		'target_image',
 		'target_video'
 	]):
-		for method in [ 'upload', 'change', 'clear' ]:
+		for method in [ 'change', 'clear' ]:
 			getattr(ui_component, method)(update_preview_frame_slider, outputs = PREVIEW_FRAME_SLIDER)
 
 	for ui_component in get_ui_components(
@@ -103,6 +104,7 @@ def listen() -> None:
 		'face_debugger_items_checkbox_group',
 		'frame_colorizer_size_dropdown',
 		'face_mask_types_checkbox_group',
+		'face_mask_areas_checkbox_group',
 		'face_mask_regions_checkbox_group'
 	]):
 		ui_component.change(update_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE)
@@ -110,6 +112,7 @@ def listen() -> None:
 	for ui_component in get_ui_components(
 	[
 		'age_modifier_direction_slider',
+		'deep_swapper_morph_slider',
 		'expression_restorer_factor_slider',
 		'face_editor_eyebrow_direction_slider',
 		'face_editor_eye_gaze_horizontal_slider',
@@ -126,8 +129,10 @@ def listen() -> None:
 		'face_editor_head_yaw_slider',
 		'face_editor_head_roll_slider',
 		'face_enhancer_blend_slider',
+		'face_enhancer_weight_slider',
 		'frame_colorizer_blend_slider',
 		'frame_enhancer_blend_slider',
+		'lip_syncer_weight_slider',
 		'reference_face_distance_slider',
 		'face_selector_age_range_slider',
 		'face_mask_blur_slider',
@@ -142,6 +147,7 @@ def listen() -> None:
 	for ui_component in get_ui_components(
 	[
 		'age_modifier_model_dropdown',
+		'deep_swapper_model_dropdown',
 		'expression_restorer_model_dropdown',
 		'processors_checkbox_group',
 		'face_editor_model_dropdown',
@@ -158,7 +164,9 @@ def listen() -> None:
 		'face_detector_model_dropdown',
 		'face_detector_size_dropdown',
 		'face_detector_angles_checkbox_group',
-		'face_landmarker_model_dropdown'
+		'face_landmarker_model_dropdown',
+		'face_occluder_model_dropdown',
+		'face_parser_model_dropdown'
 	]):
 		ui_component.change(clear_and_update_preview_image, inputs = PREVIEW_FRAME_SLIDER, outputs = PREVIEW_IMAGE)
 
@@ -178,8 +186,8 @@ def clear_and_update_preview_image(frame_number : int = 0) -> gradio.Image:
 
 def slide_preview_image(frame_number : int = 0) -> gradio.Image:
 	if is_video(state_manager.get_item('target_path')):
-		preview_vision_frame = normalize_frame_color(get_video_frame(state_manager.get_item('target_path'), frame_number))
-		preview_vision_frame = resize_frame_resolution(preview_vision_frame, (1024, 1024))
+		preview_vision_frame = normalize_frame_color(read_video_frame(state_manager.get_item('target_path'), frame_number))
+		preview_vision_frame = restrict_frame(preview_vision_frame, (1024, 1024))
 		return gradio.Image(value = preview_vision_frame)
 	return gradio.Image(value = None)
 
@@ -190,7 +198,13 @@ def update_preview_image(frame_number : int = 0) -> gradio.Image:
 	conditional_append_reference_faces()
 	reference_faces = get_reference_faces() if 'reference' in state_manager.get_item('face_selector_mode') else None
 	source_frames = read_static_images(state_manager.get_item('source_paths'))
-	source_faces = get_many_faces(source_frames)
+	source_faces = []
+
+	for source_frame in source_frames:
+		temp_faces = get_many_faces([ source_frame ])
+		temp_faces = sort_faces_by_order(temp_faces, 'large-small')
+		if temp_faces:
+			source_faces.append(get_first(temp_faces))
 	source_face = get_average_face(source_faces)
 	source_audio_path = get_first(filter_audio_paths(state_manager.get_item('source_paths')))
 	source_audio_frame = create_empty_audio_frame()
@@ -210,7 +224,7 @@ def update_preview_image(frame_number : int = 0) -> gradio.Image:
 		return gradio.Image(value = preview_vision_frame, elem_classes = [ 'image-preview', 'is-' + detect_frame_orientation(preview_vision_frame) ])
 
 	if is_video(state_manager.get_item('target_path')):
-		temp_vision_frame = get_video_frame(state_manager.get_item('target_path'), frame_number)
+		temp_vision_frame = read_video_frame(state_manager.get_item('target_path'), frame_number)
 		preview_vision_frame = process_preview_frame(reference_faces, source_face, source_audio_frame, temp_vision_frame)
 		preview_vision_frame = normalize_frame_color(preview_vision_frame)
 		return gradio.Image(value = preview_vision_frame, elem_classes = [ 'image-preview', 'is-' + detect_frame_orientation(preview_vision_frame) ])
@@ -225,7 +239,7 @@ def update_preview_frame_slider() -> gradio.Slider:
 
 
 def process_preview_frame(reference_faces : FaceSet, source_face : Face, source_audio_frame : AudioFrame, target_vision_frame : VisionFrame) -> VisionFrame:
-	target_vision_frame = resize_frame_resolution(target_vision_frame, (1024, 1024))
+	target_vision_frame = restrict_frame(target_vision_frame, (1024, 1024))
 	source_vision_frame = target_vision_frame.copy()
 	if analyse_frame(target_vision_frame):
 		return cv2.GaussianBlur(target_vision_frame, (99, 99), 0)

facefusion/uis/components/processors.py

@@ -3,8 +3,8 @@ from typing import List, Optional
 import gradio
 
 from facefusion import state_manager, wording
-from facefusion.filesystem import list_directory
-from facefusion.processors.core import clear_processors_modules, get_processors_modules
+from facefusion.filesystem import get_file_name, resolve_file_paths
+from facefusion.processors.core import get_processors_modules
 from facefusion.uis.core import register_ui_component
 
 PROCESSORS_CHECKBOX_GROUP : Optional[gradio.CheckboxGroup] = None
@@ -26,15 +26,24 @@ def listen() -> None:
 
 
 def update_processors(processors : List[str]) -> gradio.CheckboxGroup:
-	clear_processors_modules(state_manager.get_item('processors'))
-	state_manager.set_item('processors', processors)
-
 	for processor_module in get_processors_modules(state_manager.get_item('processors')):
+		if hasattr(processor_module, 'clear_inference_pool'):
+			processor_module.clear_inference_pool()
+
+	for processor_module in get_processors_modules(processors):
 		if not processor_module.pre_check():
 			return gradio.CheckboxGroup()
+
+	state_manager.set_item('processors', processors)
 	return gradio.CheckboxGroup(value = state_manager.get_item('processors'), choices = sort_processors(state_manager.get_item('processors')))
 
 
 def sort_processors(processors : List[str]) -> List[str]:
-	available_processors = list_directory('facefusion/processors/modules')
-	return sorted(available_processors, key = lambda processor : processors.index(processor) if processor in processors else len(processors))
+	available_processors = [ get_file_name(file_path) for file_path in resolve_file_paths('facefusion/processors/modules') ]
+	current_processors = []
+
+	for processor in processors + available_processors:
+		if processor in available_processors and processor not in current_processors:
+			current_processors.append(processor)
+
+	return current_processors